Method for acquiring an image set of intraoral objects - Patent Application 20070122997

Abstract

The present invention relates to a method for acquiring a set of images covering targets belonging to objects in a user's mouth, the method comprising the steps of: 1) presenting to a user on a screen (12) and using spatial augmented reality with respect to the intraoral objects observed by an image acquisition device (10), a multidimensional symbol or a set of multidimensional symbols (24), the shape and / or position of each symbol being determined to indicate to the user at least one predetermined acquisition condition suitable for acquiring such an image; and 2) acquiring, for each symbol, such an image using an acquisition device when the at least one predetermined acquisition condition associated with the symbol is met, preferably when all predetermined acquisition conditions associated with the symbol are met.

Description

[Technical Field]

[0001] The present invention relates to a method for acquiring an image set of intraoral objects, particularly dental objects, and in particular the dental arch of a user, and also to a device for implementing such a method. [Background technology]

[0002] To analyze a user's dental condition, particularly before establishing orthodontic treatment, it is conventional to acquire a set of images covering a target located in the user's oral cavity, specifically the user's dental arch. An image "covers" a target when it at least partially represents the target. An image set "covers" a target when it includes images covering the target from different viewing directions, specifically to provide precise three-dimensional information about the target.

[0003] Obtaining at a dental office, or more generally from a dental care professional, can involve significant expense and stress for the user.

[0004] Alternatively, a user can acquire dental images themselves, for example, using their mobile phone. To acquire images, a user typically looks into a mirror, which can make it difficult to precisely position the phone. Furthermore, until the user examines the gallery in which the images are stored, the person does not know whether the images are of good quality or whether they accurately cover the intended target. Even when examining the gallery, the user cannot accurately assess whether the coverage of the target by the acquired image set is sufficient. Finally, acquisition can be labor-intensive if the user must repeat it. Frustrated by these difficulties, the user may prematurely terminate the acquisition operation.

[0005] There is a need to facilitate the acquisition of a set of images of a target, specifically a mouth, that covers all or part of a dental arch, while limiting the risk of an incomplete or poor quality acquisition.

[0006] One object of the present invention is to meet this need. Summary of the Invention

[0007] The present invention proposes a method for obtaining an image set that covers targets belonging to objects in the user's mouth, preferably with a coverage rate equal to or greater than a coverage threshold, for example, an image set that covers the incisors or teeth (targets) of the user's dental arch (objects in the mouth).

[0008] According to a first main aspect of the present invention, a method is provided comprising the steps of: 1) presenting to the user on a screen and using spatial augmented reality with respect to an intraoral object observed by an image acquisition device, preferably an image acquisition device being handled by the user, a multidimensional symbol or a set of multidimensional symbols, the shape and / or position of each symbol being determined to indicate to the user at least one predetermined acquisition condition suitable for acquiring such an image; 2) for each symbol, capturing such an image using a capture device when at least one predetermined capture condition associated with the symbol is satisfied, preferably when all predetermined capture conditions associated with that symbol are satisfied.

[0009] As will be explained in more detail below, the shape of the multidimensional symbol in the space of the real scene observed by the capture device can be associated with the symbol when the user looks at the screen, informing and guiding the user of one or more capture conditions suitable for capturing the desired image. Thus, symbols presented in augmented reality provide particularly effective guiding information.

[0010] The method according to the first main aspect of the invention may also include, in particular, one or more of the following optional features: - in step 2), an image is captured by the capture device only if at least one predetermined capture condition associated with at least one symbol is fulfilled, preferably only if all predetermined capture conditions associated with said symbols are fulfilled, -At least one symbol must be said symbol axis, preferably a rotation axis, wherein the acquisition condition is an angular deviation between the optical axis of the acquisition device and the symbol axis of less than 20°, preferably less than 10°, preferably less than 5°, preferably substantially zero, which is substantially perfect alignment of the optical axis of the acquisition device with said symbol axis, and / or - defining a dimension on the representation of a symbol on a screen that is variable as a function of the distance between the acquisition device and said symbol in augmented reality, said acquisition condition being a predetermined specific value for said dimension or the attribution of said dimension to a predetermined specific range of values ​​for said dimension, for example said dimension being 1 mm; - before step 1), the user is instructed, for each symbol, of the at least one predetermined acquisition condition associated with said symbol, for example the user is instructed that, for each symbol, in order to acquire the image set, the axis of the symbol must be aligned as closely as possible with the optical axis of the acquisition device and / or the user must try to view the symbol on a screen so that the dimension is as close as possible to the specific value, the instruction is carried out by a tutorial, which preferably makes it possible to progressively teach all the functions of the computer program executed to implement the method, the tutorial being upgradable based on updates; - in step 2), images are automatically acquired using an acquisition device when predetermined acquisition conditions are met, the acquisition conditions defining the position in space of the acquisition device and / or its orientation around its optical axis and including said at least one acquisition condition indicated by a symbol, - in step 2), if such an image is acquired using an acquisition device, - the appearance of the symbol is modified or the symbol is removed; and / or - an audible signal is emitted, and / or - a score displayed on the screen and related to the coverage rate of the target by the previously acquired images and / or related to the duration for the acquisition of the previously acquired images and / or related to the quality of the previously acquired images and / or related to the usefulness of the previously acquired images is modified; - when the image set is acquired, the ranking determined as a function of said score is presented to the user on a screen, - the screen displays a symbol on a preview image representing the real scene observed by the acquisition device or on a view of a model representing at least the object or the target in the mouth, such as said preview image; the screen displays reference marks at fixed positions on the screen, the reference marks preferably having a constant shape, and when a predetermined acquisition condition associated with said symbol is met, such symbol preferably has a shape complementary to the reference mark; the target comprises more than 2, preferably more than 5 and / or less than 32 teeth, and / or the image set comprises more than 2, more than 5, more than 10 and / or less than 1,000 images taken under different respective acquisition conditions, and / or the symbol set comprises more than 2, more than 5 and / or less than 100 symbols, the symbols preferably each have an axis oriented towards the centre of the user's mouth; the symbols are preferably distributed in one plane, preferably in two planes, preferably in three planes, preferably in the occlusal plane for obtaining images with a viewing axis, in a plane inclined relative to the occlusal plane for obtaining a top view relative to the occlusal plane, and in a plane inclined relative to the occlusal plane for obtaining a bottom view relative to the occlusal plane, In the space of intraoral objects for augmented reality representation, the symbols are outside the user's mouth, and therefore the acquired images are extraoral.

[0011] In one embodiment, the symbol is a portion of the target surface, and the preview image or equivalent image displays a reticle for visualizing the angle of the acquisition device, the reticle being displayed on the target surface in the extension of the optical axis, in the same way that a reticle appears on an object when aimed with a firearm that projects a laser beam onto the object, depending on the direction of the shot.

[0012] Therefore, to correctly orient the capture device, the user must aim at the symbol represented on the target surface.

[0013] In this embodiment, the symbol can be a point or a surface. If it is a surface, its contour deforms according to the shape and distance of the target surface onto which it is projected. The symbol can be advantageously used to indicate the distance of the acquisition device from the target and / or the orientation of the acquisition device about its optical axis.

[0014] The shape of the sight is not limited.

[0015] Specifically, the symbol may be a thumbnail, a small image attached to a tooth, such as a star in a video game.

[0016] The symbol set preferably defines the acquisition conditions for the following acquisitions: at least one image taken towards the user and / or at least one image taken towards the user's right and / or at least one image taken towards the user's left, preferably at least one image taken towards the user, at least one image taken towards the user's right and at least one image taken towards the user's left; and / or - on the one hand, at least one image taken towards the user, and on the other hand, at least one image taken from above the user and / or at least one image taken from below the user, preferably at least one image taken towards the user and at least one image taken from above the user and at least one image taken from below the user; and / or -At least one image taken with the mouth open and / or at least one image taken with the mouth closed.

[0017] The invention further relates to a device for implementing the method according to the first main aspect of the invention, the device comprising: an image acquisition device, preferably in the form of a mobile phone; a computer, preferably integrated in or in communication with the acquisition device, having a computer program comprising program code instructions, the program code instructions - in step 1), placing and presenting to the user, in a spatial augmented reality of the intraoral object, one or more multidimensional symbols on a screen, preferably on the screen of an acquisition device, the shape and / or position of the symbols being determined to indicate to the user at least one predetermined acquisition condition suitable for acquiring such an image; - preferably in step 2), allowing the acquisition device to acquire such an image only if said at least one predetermined acquisition condition associated with the symbol is fulfilled and / or instructing the acquisition device to acquire such an image only if said at least one predetermined acquisition condition is fulfilled, and / or updating the coverage level of the target by the acquired images, preferably comparing the coverage level with a coverage threshold and preferably presenting information on the coverage level and / or information on the difference between the coverage threshold and the coverage level on a screen.

[0018] The acquisition device preferably comprises: - a mobile phone, the screen of which is integrated into the mobile phone, or - A device equipped with a camera and a holder designed to be held against the user, and in particular against the user's teeth and / or gums, during image acquisition, with a screen either integrated into the holder or at a distance from the holder.

[0019] According to a second main aspect of the present invention, a method is provided for rapidly covering a target with a coverage rate equal to or greater than a coverage threshold, the method comprising: a) capturing at least one image using an image capture device, preferably a mobile phone, preferably by a user; b) updating a target coverage level as a function of the at least one image acquired in step a); c) If the coverage level is below the coverage threshold: - determining guide information that guides a user towards suitable acquisition conditions for acquiring additional images with an image acquisition device that increase the coverage level; - presenting to the user guide information and preferably information about the coverage level and / or the difference between the coverage threshold and the coverage level, information that allows the user to know the progress of the acquisition of the image set; - correcting, by the user, the position and / or orientation of the acquisition device as a function of the guide information and repeating step a), preferably in real time, wherein the acquired images are preferably extracted from a video that the user views on the screen of the acquisition device.

[0020] As will be explained in more detail below, determining the guide information as a function of the coverage rate updated in real time advantageously facilitates the acquisition of images of a user's mouth, and in particular the acquisition of dental images. Specifically, the user receives real-time guide information, which makes the acquisition more efficient, especially when the guide information is selected to guide the user toward optimal acquisition conditions that enable the acquisition of additional images that maximize the increased coverage level.

[0021] With the guidance, the user does not need to visit a dental professional or be supervised by a dental professional to acquire the images. Advantageously, the images can be acquired under precise acquisition conditions without any special training. Specifically, they can be acquired by the user themselves or by one of the user's relatives. In particular, the method facilitates the acquisition of images of a child's arch by parents.

[0022] The presentation of information about coverage level is also particularly advantageous because it effectively discourages the user from interrupting the acquisition before it is complete. This makes acquisition particularly comfortable, and may even be enjoyable, since the user always knows how far they have to go before acquiring the entire image set.

[0023] The method according to the second main aspect of the invention may also include, in particular, one or more of the following optional features: -the following is displayed on the screen, preferably on the screen of the acquisition device, preferably a mobile phone: - Target representation, a representation of the part of the target covered by step a) or one or more images acquired in a previous step a), and - preferably a representation of an object in the mouth when the object in the mouth includes a part of the user's mouth other than the target; the guide information and / or the information about the coverage level and / or the information about the difference between the coverage threshold and the coverage level are displayed on the screen of the acquisition device and are presented in augmented reality in a preview image that is representative of the real scene observed by the acquisition device and / or in an image equivalent to the preview image that is representative of a theoretical scene that symbolically or realistically represents all or some of the elements of the real scene in the same arrangement as the real scene, the equivalent image preferably comprises a view of a model of at least a part of said real scene, the model being a digital three-dimensional model; the information about the coverage level and / or the difference between the coverage threshold and the coverage level is presented in a spatial reference frame so as to constitute so-called guide information, - information about the coverage level and / or information about the difference between the coverage threshold and the coverage level is presented on a representation of the target, applying an appearance, preferably a color or texture, to an area of ​​said representation that differs depending on whether said area is covered by at least one acquired image, or - applying an appearance to a predetermined part of the target, for example a symbol representing a tooth, which appearance differs depending on whether the part is covered or not, preferably by making a symbol appear or disappear on the screen of the acquisition device, or applying an appearance to a symbol indicative of at least one acquisition condition, the appearance being different depending on whether the image was acquired with the at least one acquisition condition; the targets comprise a set of teeth and / or soft tissues, the preview image or equivalent image is updated in real time, preferably on the user's mobile phone screen, the covered teeth are specifically marked by a symbol or by applying an appearance that allows them to be distinguished from uncovered teeth, a tooth is "covered" when its first surface that is covered is covered, - a plurality of symbols are anchored in augmented reality to the real scene observed by the acquisition device so as to appear in the preview image or an equivalent image, each symbol being anchored, for example, to a respective tooth of the user or to indicate to the user suitable acquisition conditions for the acquisition of additional images; - the symbol is a three-dimensional symbol according to the first main aspect of the invention, - in step a) the user targets such a symbol, preferably two-dimensional or three-dimensional, with the acquisition device, - at least one image is acquired, preferably automatically, i.e. without specific user intervention, when the target symbol is reached, preferably when the target symbol is at least partially superimposed on a fixed reference mark displayed on the screen of the acquisition device, Symbols are anchored in augmented reality to adjacent or non-adjacent teeth on the preview image or on an equivalent image, for example symbols can be anchored regularly along the dental arch, for example every 2 or 3 teeth. the symbol is anchored and / or shaped to define, optionally in cooperation with such reference marks, a predetermined acquisition condition, preferably a distance of the acquisition device from the target and / or an orientation of the acquisition device about its optical axis and / or an angle of said optical axis relative to the target; - in step b), the at least one image acquired in step a) is analyzed, preferably by a neural network, in order to identify a representation of a target on the image, and then a corresponding area in the preview image is marked, preferably by coloring it with a color associated with the target, - in step a), before or after image acquisition, the quality of the acquired or previewed image displayed on the screen of the acquisition device, preferably at least the sharpness and / or contrast and / or color balance of the image and / or the distance of the acquisition device from the target and / or the orientation of the acquisition device around its optical axis and / or the angle of said optical axis relative to the target, respectively, is evaluated, and an image is acquired and / or the coverage rate is updated only if the quality exceeds a predetermined quality threshold; In step c), A number of suitable acquisition conditions are tested for acquisition by the image acquisition device of additional images with increasing levels of coverage, and then the guide information is determined to guide the user to optimal acquisition conditions, i.e., acquisition conditions suitable for acquiring additional images with the image acquisition device that will most likely increase the coverage level; In step b), Each acquired image is at least one first neural network trained to detect target expressions in images and / or an image processing algorithm adapted to detect target expressions in images; a second neural network trained to determine the position and orientation of the acquisition device during image acquisition, and thus the direction of the acquisition device's optical axis relative to the target, which is the acquisition device's camera, and the acquisition device's distance from the target; - the target representation is projected onto a model of the intraoral target or object, or "reference model," along a projection direction oriented as the direction of the optical axis relative to the target, the target representation being virtually (i.e., theoretically) positioned relative to the reference model when the acquisition device is in relation to the target, and then - a coverage rate is determined as a function of the area of ​​the reference model covered by said projection and by said projection generated in any previous step b), In step b), Each acquired image is a first neural network trained to detect representations of the target or salience of the target in an image; a second neural network trained to recognize a corresponding region of the reference image from a representation of the target or the point of interest in the image; and - a coverage rate is determined as a function of the area of ​​the reference image covered by the corresponding region and by the corresponding region determined in any previous step b), - The acquisition device a mobile phone with a screen, preferably the user's own mobile phone, or a device, a holder equipped with a camera and held against a user during the acquisition of an image set, preferably allowing the mouth to open and close, preferably partially introduced into the user's mouth, preferably resting against the gums and / or teeth; a screen for displaying the scene observed by the camera, said screen being integrated into the holder or at a distance from the holder, - in step a), the user visualizes in real time on the screen of said mobile phone the actual scene observed by said mobile phone or the corresponding theoretical scene, the images being preferably acquired automatically when the mobile phone observes the target under predetermined acquisition conditions, preferably under acquisition conditions determined in step c) of the previous cycle of steps a) to c), - in step c), the user is presented with a counter or gauge, preferably in the form of a progress bar, preferably on the screen of the acquisition device, providing information on the coverage level and / or on the difference between the coverage threshold and the coverage level; and / or - When the coverage threshold is reached, a score calculated as a function of the time taken to reach the coverage threshold and / or the quality of the acquired images and / or the usefulness of the acquired images is presented to the user, preferably on the screen of the acquisition device, and / or a ranking determined as a function of said score is presented to the user, preferably on the screen of the acquisition device.

[0024] In a first main embodiment, the guide information comprises a set of symbols positioned in augmented reality as a function of each image acquired. The acquired set of images comprises one image for each symbol. In step a), the user must point their mobile phone at the symbols and select a symbol, as in a video game. For example, each symbol may be anchored in augmented reality to a respective tooth, with the target being constituted by the tooth and / or soft tissue.

[0025] Symbols may be anchored, for example, to non-adjacent teeth, for example, every two or three teeth, according to the desired acquisition conditions.

[0026] The fiducial marks may be depicted on the screen of the user's mobile phone. When the fiducial mark overlaps with a symbol, the character is selected, and then an image is preferably automatically acquired, and the symbol is marked or erased. The marking or erasure of the symbol provides information about the coverage rate. Also, guide information is provided so that the user can easily find symbols that have not yet been selected on the preview image displayed on the mobile phone screen. The user can position the mobile phone accordingly. When all symbols are selected, the image set covers all targeted teeth and / or soft tissues. The coverage level may be, for example, the ratio of the number of symbols reached to the initial number of symbols before acquisition begins.

[0027] In one variation of the first main embodiment, the symbol is anchored and / or shaped to cooperate with the reference mark to define a predetermined acquisition condition, preferably the distance of the acquisition device from the target and / or the orientation of the acquisition device about its optical axis and / or the angle of said optical axis relative to the target.

[0028] In one embodiment, the optional fiducial mark is shaped to be superimposed simultaneously on multiple symbols, for example, two or three symbols. For example, it includes multiple base fiducial marks, such as circles, that must be superimposed simultaneously on each of the multiple symbols. Advantageously, this superimposition corresponds to a predetermined angle and distance of the acquisition device from the target. Preferably, symbols in the multiple symbols have an appearance, e.g., color, that is specific to the multiple symbols. For example, a user may first aim to place three green symbols within the fiducial mark circle, followed by three red symbols, etc.

[0029] Similarly, to impose a predetermined distance of the acquisition device from the target, the reference mark and symbol may have compatible dimensions such that when the user accurately aligns the reference mark and symbol, the acquisition device and target are separated by that distance.

[0030] The symbols of the plurality of symbols and the base reference mark are preferably different from each other, for example they have different numbers. For example, a user aims to place three symbols numbered 1, 2, and 3 in the circles numbered 1, 2, and 3 on the reference mark, respectively. Advantageously, if the base reference marks are not aligned, this superposition can impose a predetermined orientation of the acquisition device about its optical axis.

[0031] Similarly, to impose an orientation, the reference marks and symbols may have a non-rotated shape, for example a rectangular shape, preferably a shape without symmetry, so that the user can only superimpose the reference marks and symbols in the same orientation when the acquisition device is oriented in one or more predetermined orientations around the optical axis.

[0032] In particular, when symbols are used to impose angles, distances, or orientations on the acquisition device, they are not necessarily associated with a particular tooth, specifically the tooth to be covered.

[0033] In the second main embodiment, a view of a three-dimensional model of a target, e.g., a set of teeth, is displayed on a mobile phone screen. In one embodiment, the user can modify this view, i.e., change the observation point of the model, using conventional model manipulation software. In a preferred embodiment, the view is modified according to the conditions under which the target is observed by the mobile phone, preferably according to the principles of augmented reality. The template is then displayed, possibly transparently, superimposed on the preview image or can replace the preview image. Once the preview image covers the target, an image is preferably acquired automatically. The area of ​​the target shown on the acquired image is marked on the model, preferably colored green, for example. Areas of the target that remain to be covered are shown differently, for example, colored red. Thus, the user can immediately see the coverage rate, e.g., the ratio between the green area and the sum of the red and green areas. The unmarked areas guide the user toward acquisition conditions that will increase the coverage rate.

[0034] In a variation of the second main embodiment, the reference model view is replaced by a reference image, for example a photograph, for example a panoramic photograph.

[0035] Preferably, the method according to the invention comprises: at least one image taken towards the user and / or at least one image taken towards the user's right and / or at least one image taken towards the user's left, preferably at least one image taken towards the user, at least one image taken towards the user's right and at least one image taken towards the user's left; and / or - on the one hand, at least one image taken towards the user, and on the other hand, at least one image taken from above the user and / or at least one image taken from below the user, preferably at least one image taken towards the user and at least one image taken from above the user and at least one image taken from below the user; and / or - implemented to acquire at least one image taken with the mouth open and / or at least one image taken with the mouth closed.

[0036] The invention further relates to a device for implementing the method according to the invention, comprising: an image acquisition device, a camera-equipped computer, in particular a mobile phone or tablet, preferably a mobile phone, or a camera-equipped mirror, for acquiring a set of images, in particular for carrying out step a), a computer, which may be an acquisition device, preferably integrated into or in communication with a mobile phone, having a computer program comprising program code instructions, the program code instructions Presenting three-dimensional symbols providing guide information in augmented reality according to the first main aspect of the invention; and / or According to a second main aspect of the present invention, - updating the coverage level in step b); comparing the coverage level to a coverage threshold; if the coverage level is below the coverage threshold, determining guide information and presenting the guide information and preferably information about the coverage level and / or information about the difference between the coverage threshold and the coverage level to the user in step c), - Preferably, it comprises a screen, preferably a computer screen, for displaying guide information and, according to the second main aspect of the invention, information about the coverage level and / or information about the difference between the coverage threshold and the coverage level.

[0037] In a preferred embodiment, the computer program is executed by the image acquisition device, whereby the computer program can be integrated into dedicated software, in particular dedicated software for mobile phones or tablets.

[0038] The screen may be integrated into the image capture device, preferably the screen is a mobile phone or tablet screen.

[0039] Preferably, the screen and computer program are integrated into the image capture device.

[0040] The user can then easily obtain images of the target in good quality and together cover the entire target with a simple mobile phone or tablet without the intervention of a third party, in particular without the intervention of a dental treatment professional.

[0041] The device may further comprise communication means, in particular for transmitting acquired images and / or receiving model or reference images.

[0042] Of course, required or optional features of the various main aspects of the invention may be combined, unless they are technically compatible.

[0043] definition A "user" is a person for whom the method according to the invention is implemented.

[0044] The term "dental care professional" refers to any person qualified to provide dental care, including orthodontists and dentists.

[0045] "Arch" or "dental arch" means all or part of a dental arch, preferably at least two, preferably at least three, most preferably at least four teeth. According to the international agreement of the FDI World Dental Federation, each tooth in a dental arch has a predetermined number.

[0046] "Soft tissue" is the part of the mouth covered by skin, such as the gums, palate, or tongue, as opposed to teeth or braces.

[0047] Soft tissues are extraskeletal supportive tissues such as adipose tissue, tendons, ligaments, fascia, skin, etc. (soft connective tissue), as well as muscle, blood vessels, and nerve tissue (non-connective tissue).

[0048] A "retractor" is a device for curling the lips, or more generally, for moving the lips away from the teeth. It preferably includes upper and lower flanges and / or right and left flanges that extend around the retractor opening and are intended to be inserted between the teeth and the lips. In the operating position, the user's lips rest on these edges, resulting in the teeth being visible through the retractor opening. The retractor thus allows for viewing of the teeth without obstruction by the lips. However, the teeth do not rest on the retractor, so by rotating the head relative to the retractor, the user can change the teeth visible through the retractor opening. The user can also change the spacing between dental arches. Specifically, the retractor does not push the teeth to spread the two jaws apart, but rather the lips. In one embodiment, the retractor is configured to elastically spread the upper and lower lips to expose the teeth visible through the retractor opening. In one embodiment, the retractor is configured so that the distance between the top and bottom edges and / or the right and left edges is constant. Retractors are described, for example, in PCT / EP2015 / 074896, U.S. Patent No. 6,923,761, or U.S. Patent No. 2004 / 0209225.

[0049] By "computer" is meant a computer processing unit, including a set of several machines with computer processing capabilities. In particular, this unit may be integrated into a mobile phone, in particular the user's mobile phone, or it may be a PC-type computer or a server, for example a server remote from the user, for example a computer located in the "cloud" or at the dental care professional's premises. The mobile phone and the computer then have means to communicate with each other.

[0050] Typically, the computer comprises a processor, a memory, a human-machine interface, typically comprising a screen, and a communication module via the Internet, WIFI, Bluetooth, or a telephone network. Software configured to implement the method of the invention is loaded into the computer's memory. The computer may also be connected to a printer.

[0051] The method according to the invention (other than the capturing operations performed by the image capturing device and the operations of moving the image capturing device performed by the user) is implemented by a computer, preferably exclusively by a computer.

[0052] A "real scene" consists of a set of elements simultaneously observed by an acquisition device. The view of the actual scene observed by the acquisition device is conventionally displayed on the screen of the acquisition device in the form of a "preview image" that is continuously updated in real time, like a film.

[0053] The preview image may be replaced or supplemented by an equivalent image that is a symbolic or realistic representation of a theoretical scene that represents all or some of the elements of the real scene in the same arrangement as in the real scene, i.e., in such a way that the represented elements are positioned relative to one another as in the real scene. The equivalent image is a view of the theoretical scene under viewing conditions identical to those used by the capture device to observe the real scene and acquire the preview image. Thus, the contours of the representations of physical elements on the equivalent image are superimposable on the contours of those physical elements on the preview image. The equivalent image is selected to match the preview image as closely as possible.

[0054] The preview image is preferably displayed on the screen of the capture device, although in one embodiment an equivalent image replaces the preview image on the screen. However, capturing an image with the capture device at a given time consists of recording the preview image as it is displayed or as it would have been displayed if replaced by the equivalent image.

[0055] Augmented reality is a form of communication in which visual elements are added to an image to represent a scene realistically or symbolically.

[0056] In particular, visual elements may be added to a preview image, or equivalent image, that represents the actual scene as viewed by the capture device.

[0057] In a preferred embodiment, augmented reality is used so that when an image representing the target is acquired in step a), the screen represents, in real time, a realistic or symbolic representation of the target as observed by the image acquisition device.

[0058] A symbol is "anchored" in augmented reality when it appears fixed in the real or theoretical scene as the capture device moves relative to the real scene (thus modifying the image displayed by the capture device).

[0059] The symbols appearing in the augmented reality may be points, two-dimensional extending in a plane in the space of intra-oral objects, or preferably three-dimensional extending virtually in all three dimensions of the space of intra-oral objects. How the two-dimensional or three-dimensional symbol is represented depends on the conditions under which it is virtually observed. For example, its size depends on the observation distance. Preferably, the symbol is not spherical, so that the representation of the symbol also provides information about the angle and / or orientation of the acquisition device around its optical axis. Symbols providing guide information are preferably displayed on a preview image or equivalent.

[0060] The term "model" means a three-dimensional digital model. A model is made up of a set of voxels.

[0061] A "tooth model" is a three-dimensional digital model of teeth. A dental arch model can be cut to define tooth models for at least some, and preferably all, of the teeth represented in the arch model. Thus, a tooth model is a model within the arch model.

[0062] "Image" refers to a two-dimensional image such as a photograph or a video frame. Images are made up of pixels. A "video" can be considered a collection of photographs. The number of pixels in an image is preferably greater than 100, 1,000, 10,000, or 100,000, or 1,000,000, and / or less than 1,000,000,000.

[0063] The image represents the scene, realistically or otherwise.

[0064] Specifically, the image may represent a deformed mask resulting from the projection of an original mask, preferably by an acquisition device. The original mask may be, for example, a grid or set of dots, typically uniformly distributed. The projection may be in the form of visible or invisible light, preferably infrared light. The deformation resulting from the projection of a portion of the original mask, e.g., a dot, conveys information about the distance between the image acquisition device and the area of ​​the scene onto which this portion of the original mask is projected. It may also provide information about the orientation of that area in space. The images used by Apple's Face ID software are examples of such images, also known as "3D images."

[0065] The image acquired according to the present invention is preferably a photograph, possibly extracted from a video, and realistically represents the observed scene as perceived by the human eye. It may specifically represent a distorted mask superimposed on an image that realistically depicts the scene. It may also represent the distorted mask alone. Since the original mask is projected onto the real scene observed by the acquisition device, the image representing the distorted mask is also considered to be equivalent to a preview image.

[0066] A "match" or "fit" between two objects, for example, two images of a dental arch, is a measure of the difference or "distance" between them. The "best fit" is achieved when this difference is smallest, specifically when the two images represent the same elements in essentially the same way, i.e., in such a way that the element representations on the two images are essentially aligned and superimposable.

[0067] The "acquisition conditions" of an image specify the spatial position and / or orientation of the image acquisition device for that image relative to the target, and preferably the calibration of that image acquisition device (e.g., aperture, exposure time, focal length, and sensitivity). The symbol may indicate acquisition conditions suitable for a single position and orientation of the acquisition device. Alternatively, the symbol may indicate acquisition conditions corresponding to multiple positions and / or orientations of the acquisition device to guide toward several potential images. For example, it can guide toward a predetermined observation axis without guiding toward a specific position along this axis, thus allowing the user to freely acquire one or more images along this axis at various positions along this axis, as in the embodiment of FIG. 3. It can also guide to a predetermined position in space without guiding toward a specific orientation of the acquisition device about its optical axis, as in the embodiment shown in FIG. 5.

[0068] Image capture devices include cameras for capturing images, such as photographs or film. References to observing a scene by a capture device refer to observing the scene by a camera of the capture device. References to the optical axis of the capture device refer to the optical axis of the camera of the capture device, etc.

[0069] "Angle" is the orientation of the optical axis of the acquisition device relative to the target.

[0070] The angle between two lines is the angle formed between two planes that are perpendicular to those two lines.

[0071] Unless otherwise indicated, "including" or "comprising" or "having" is to be interpreted in an open-ended manner. [Brief explanation of the drawings]

[0072] Further features and advantages of the present invention will become apparent from the following detailed description and from a consideration of the accompanying drawings. [Figure 1]2 shows a schematic representation of the steps of a cycle of the method according to the second main aspect of the invention; [Figure 2] 1 illustrates an exemplary device according to the present invention. [Figure 3] 1 shows an example of implementing the method according to the second main aspect of the invention in the first main embodiment. [Figure 4] In the second main embodiment, examples of methods according to the first main aspect of the invention and the second main aspect of the invention are given. [Figure 5] 2 shows another example of a method according to the first main aspect of the invention and the second main aspect of the invention in a second main embodiment. [Figure 6] 6 illustrates the symbol from FIG. 5 being presented to a user when a predetermined acquisition condition associated with the symbol is met. [Figure 7] 2 shows another example of a method according to the first main aspect of the invention and a method according to the second main aspect of the invention in the second main embodiment. [Figure 8] 1 shows a schematic view of a three-dimensional symbol viewed along its axis. [Figure 9] 2 shows a schematic representation of the steps of a cycle of the method according to the second main aspect of the invention; [Figure 10] Two examples of preview images and equivalent images are shown. DETAILED DESCRIPTION OF THE INVENTION

[0073] The acquisition method according to the invention shown in FIG. 1 is implemented, for example, by a device 1 shown in FIG.

[0074] Device 1 is an image acquisition device 10 equipped with a screen 12 and loaded with a computer program; a computer 14 with a screen 18;

[0075] The computer 14 may be separate from the acquisition device or, preferably, integrated into the acquisition device.

[0076] The computer 14 may further comprise digital communication means for exchanging data 20 , specifically with the image acquisition device 10 , or further with a database 22 .

[0077] The database 22 may be partially or fully integrated into the acquisition device or computer. In particular, it may contain acquired images, reference models or images, definitions of intra-oral targets and objects, or even final models generated from the acquired images. It may also contain information about predetermined acquisition conditions associated with each symbol.

[0078] In a preferred embodiment of the present invention, the image capture device 10 is a mobile phone or a tablet. The screen 12 of the capture device is configured to present guide information, preferably information about the coverage level and / or information about the difference between the coverage threshold and the coverage level. Alternatively, or additionally, this information can be presented on a computer screen 18.

[0079] The image capture device may also be a mirror equipped with a camera.

[0080] The device 1 is used to implement the method according to the invention.

[0081] The target has a predetermined "initial coverage area", ie the area that the method is intended to cover.

[0082] A "covered area" is a portion of the initial surface to be covered that is already covered at some point during the method and is represented on at least one acquired image. A "not yet covered area" is a portion of the initial area to be covered that is not represented on any of the acquired images at a given point during the method.

[0083] The target area may include the basic area of ​​several individually identifiable organs, for example, multiple teeth. An organ may be described as "covered" or "not yet covered" depending on whether its entire basic area has been covered or not.

[0084] The intraoral object may include or consist of the tongue, and / or the palate, and / or one or two gums, and / or one or two dental arches, and / or one or more teeth. Preferably, the intraoral object is a dental arch.

[0085] The intraoral object may also be an orthodontic appliance, e.g., a buccal or lingual multi-attachment appliance, an orthodontic aligner, preferably an unobtrusive one, an assistive device, e.g., a cleat, button, or screw, or a functional training device, e.g., for correcting tongue position or treating sleep apnea.

[0086] The target may be an object within the mouth. The target may also be a region of interest within the object within the mouth, particularly a region identified as a risk region or a monitoring region, for example, as part of orthodontic treatment or periodontal follow-up, for example, a region that was insufficiently scanned or changed during a previous consultation with a dental care professional.

[0087] In a preferred embodiment, the intraoral object is a dental arch and the target is one or preferably several teeth of the dental arch.

[0088] The target is identified and communicated to the computer before the method is implemented, for example, the computer is instructed to acquire an image set covering teeth 10-14, or comprises an image or model of a dental arch in which a target representation has been identified.

[0089] The images or models used to identify the target can be generic, i.e., can be used by multiple users. They can be selected from a database, which is accessible via digital communication. The generic model can be a typodont. Preferably, the generic model or generic image is selected to represent a target having a shape close to the user's target, which improves the accuracy of the method. If the target belongs to a dental arch, the model can be generated by implementing a tooth model placement process, for example, as described in European Patent Application No. 18 184486.

[0090] The model or image used to identify the target is preferably a model or image representative of the user's target, obtained prior to implementing the method.

[0091] Each region of the target that is represented on an acquired image is said to be "covered" by that image. The sum of the regions represented on at least one acquired image is the "covered area."

[0092] An image set is considered sufficient to cover a given target when the coverage level from the acquired images reaches a coverage threshold.

[0093] The coverage threshold therefore directly or indirectly defines the percentage of the initial area covered that is considered sufficient for acquisition to be terminated, i.e., acquisition to be considered complete.

[0094] A coverage threshold of 100% means, for example, that the entire surface of the target must be represented on at least one acquired image.

[0095] The coverage threshold may be set so that the image set is sufficient to view the target from a given angle, specifically any angle.

[0096] The coverage threshold is preferably predetermined before the first step a).

[0097] The coverage threshold may be greater than 50%, 70%, 80%, 90%, or 95% of the target area. Preferably, the coverage threshold is greater than 95%.

[0098] The coverage level is a measure of the progress of the acquisition relative to the coverage threshold. Thus, before the first image is acquired, the coverage level is zero. The level of progress gradually increases with each cycle of steps a) to c).

[0099] The coverage level may be, for example, the ratio of the covered area to the initial area to be covered: if 30% of the initial area to be covered is covered, then the coverage level is 30%.

[0100] The coverage level can also be the ratio of the covered area, consisting of all regions of the target not represented on any acquired image, to the area not yet covered. If 30% of the initial area to be covered has been covered, the coverage level is 30% / 70%.

[0101] If the intraoral object includes a set of teeth, the coverage level can also be the ratio of the number of covered teeth to the number of teeth in the set. A tooth can be considered covered, for example, if at least 90% of the external, occlusal, or buccal surface of the tooth is represented on the acquired image, or better, if at least 95% of the tooth surface is represented on the acquired image, or even better, if all of the tooth surface is represented on the acquired image.

[0102] A tooth may alternatively be considered to be covered when one or more points of interest of this tooth are represented on at least one acquired image.

[0103] In the embodiment described above, it was assumed that the goal was to cover a target area.

[0104] By extension, in one embodiment, the objective is to acquire a set of images under respective acquisition conditions, preferably multidimensional, defined by respective symbols. Then, at the beginning of the implementation of the method according to the invention, symbol sets each defining an acquisition condition for one or more respective images can be assimilated to an "initial area to be covered." At a given moment, symbol sets defining acquisition conditions for which images have already been acquired can be considered the "covered area," and the number of these symbols defines the "coverage level," with the "coverage threshold" being the minimum number of these symbols. Finally, symbol sets defining acquisition conditions for which images remain to be acquired can be considered the "area not yet covered."

[0105] Also, by extension, in one embodiment, the objective is to acquire a set of images that partially represent the target, e.g., for each tooth of the target, represent points of interest such as mesiodistal points, cusps, incisal edges, points along the cervical region, or the centroid of the tooth surface. Then, at the start of the method according to the present invention, the set of points of interest on the target can be assimilated into an "initial surface to be covered." The set of target points of interest already represented on the acquired images can be considered the "covered area," and the number of these points defines the "coverage level," with the "coverage threshold" being the minimum number of these points. Finally, the set of points of interest not yet represented on the already acquired images can be considered the "area not yet covered."

[0106] One objective of the method is to guide the user during image acquisition so that the acquired image set contains as few images as possible, i.e., so that acquisition is efficient, but contains enough images to reach a coverage threshold.

[0107] The first main aspect of the present invention is to guide acquisition by means of a multidimensional symbol. The second main aspect of the present invention is to guide acquisition by informing the user of the progress of the acquisition.

[0108] First Main Aspect of the Invention In step 1) of the method according to the first main aspect of the invention shown in Figure 9, a multidimensional, i.e. two-dimensional or three-dimensional, preferably three-dimensional, symbol is positioned, i.e. "anchored", and presented to the user in augmented reality within the space of the intra-oral object, the shape and / or position of the symbol being determined to indicate to the user all or part of the acquisition conditions suitable for acquiring said image.

[0109] Of course, the user must be able to interpret the symbols. The information associated with the symbols can be explicit, for example, when it takes the form of an arrow. No training is required. Alternatively, the user can be trained to provide the user with the "rules of the game," i.e., how they are expected to handle the symbols.

[0110] The two- or three-dimensional symbols appearing in augmented reality are extended virtually, i.e. without having a physical presence, into the real scene observed by the acquisition device, or into an equivalent virtual scene, in particular a model of at least a part of the real scene, which extends in a plane or defines a volume, respectively.

[0111] As shown in Figure 7, representation in an equivalent virtual scene is advantageous.

[0112] The screen displays a preview image and / or equivalent image representative of the actual scene as observed by the capture device, specifically a view of the model corresponding to the observation of the actual scene by the capture device, and displays symbols as if they had real physical existence and were present in the actual scene.

[0113] Each symbol is associated with one or more acquisition conditions for the respective image, specifically the following acquisition conditions: a predetermined viewing axis or a predetermined range of viewing axes of the target, and / or a predetermined distance between the target and the acquisition device, or a range of such predetermined distances; and / or - a predetermined orientation around its optical axis of the acquisition device, or a range of said predetermined orientations.

[0114] The computer knows the predetermined viewing conditions associated with each symbol.

[0115] The number of symbols is adapted to the number of images in the desired image set, preferably more than 2, 5, 10, or 100 and / or less than 1,000.

[0116] The symbols, and preferably each symbol, are represented in a preview image or equivalent image, which is preferably updated in real time as the user moves the capture device.

[0117] The symbol, preferably each symbol, is preferably represented in augmented reality on the screen of the acquisition device or on the screen of a mobile phone used to communicate with the acquisition device, preferably to acquire the image.

[0118] The symbol, and preferably each symbol, is preferably anchored and / or shaped so that modifications of its representation on the screen resulting from movement of the capture device alert the user to the fact that the movement is moving away from or towards a predetermined capture condition associated with the symbol.

[0119] the predetermined acquisition condition defines a predetermined viewing axis of the target by the acquisition device, and / or a predetermined distance of the acquisition device from the target, preferably along the viewing axis, and / or a predetermined orientation of the acquisition device around its optical axis; Said modification of the representation of the symbols on said screen preferably occurs when said movement: the fact that it reduces or increases the angular difference between the optical axis of the acquisition device and the predetermined observation axis, i.e. improves or worsens the angle of the acquisition device; and / or - the fact that it reduces or increases the difference between the distance between the acquisition device and the target and the predetermined distance, and / or the fact that it reduces or increases the difference between the orientation of the acquisition device about its optical axis and the predetermined orientation, Preferably, the user is informed of the fact that each of the three differences above is reduced or increased.

[0120] The principles of augmented reality are well known and determining such angle and / or distance and / or orientation differences presents no particular difficulty to a person skilled in the art.

[0121] Preferably, the multidimensional symbol, and preferably each multidimensional symbol, defines a primary direction or "symbol axis", e.g., axis of rotation, that is identifiable by the user, and has a shape that indicates that predetermined axis of view associated with the symbol.

[0122] The multidimensional symbol, preferably each multidimensional symbol, has dimensions that, when the optical axis of the acquisition device is coincident with the main direction, on the representation of the symbol on the screen, are variable as a function of the position of the acquisition device along the optical axis, i.e. as a function of the distance between the acquisition device and the symbol.

[0123] The dimension can be assessed by observation of the screen by a user, who knows the value of the dimension that defines the position of the capture device at a predetermined distance associated with the symbol.

[0124] For example, the multidimensional symbol preferably takes the form of a superposition of rings of different diameters, the predetermined orientation is obtained when the centers of the rings are aligned along the optical axis of the acquisition device, i.e. when said centers appear overlapping on the screen; and / or The predetermined distance is obtained when the centers of the rings are aligned along the optical axis and the spacing between the rings as they appear on the screen, preferably on a representation of the symbol in a preview image or equivalent image, has a predetermined value, for example when a first ring appears adjacent to a second ring, i.e. when the inner contour of the first ring is in contact with the outer contour of the second ring.

[0125] In step 2), an image is captured if a predetermined capture condition associated with the symbol is met.

[0126] In particular, the acquisition may be performed in step a) as described below: The images may be of the type described below for step a).

[0127] The images are then analyzed to determine the acquisition conditions.

[0128] In one embodiment, each acquired image is processed by the following steps: a first neural network trained to detect representations of targets in images and / or salience points of the targets; and a second neural network trained to recognize the acquisition conditions, in particular the angle and / or distance of the acquisition device from the target, from the representation of the target in the image or the representation of the point of interest.

[0129] The first neural network may be selected in particular from object detection networks, in particular from the neural networks listed below in the section on step b2). For example, the neural network may be selected from 1000 past images, As input, past images representing past targets and / or points of interest; and As output, the neural network is trained by presenting representations of the past targets and / or points of interest on past images.

[0130] Thus, the neural network learns to recognize representations of targets and / or points of interest in new images.

[0131] The second neural network may be specifically selected from networks dedicated to image classification called "CNN" ("Convolutional Neural Network"), such as AlexNet (2012), ZF Net (2013), VGG Net (2014), GoogleNet (2015), Microsoft ResNet (2015), Caffe: BAIR Reference CaffeNet, BAIR AlexNet, Torch: VGG_CNN_S, VGG_CNN_M, VGG_CNN_M_2048, VGG_CNN_M_1024, VGG_CNN_M_128, VGG_CNN_F, VGG ILSVRC-2014 16 layers, VGG ILSVRC-2014 19 layers, Network-in-Network (Imagenet & CIFAR-10), Google: Inception (V3, V4). For example, the neural network is trained by presenting the neural network with over 1,000 past images, as input, past images representing past targets and / or points of interest, and as output, the "past" acquisition conditions of the past images.

[0132] Thus, for each new image, the neural network learns to define the conditions for its acquisition.

[0133] Determining the conditions for acquiring the images may also be achieved by searching for views of the model of the user's arch corresponding to the images, for example using an optimization operation, preferably a metaheuristic method, preferably evolutionary, preferably simulated annealing. Examples of such searching are described, for example, in International Application PCT / EP2015 / 074859, European Patent Application No. 18 184477.0 or WO 2016 / 066651.

[0134] Preferably, when the symbol is viewed along a predetermined viewing axis and / or when the capture device is at said predetermined distance and / or when the capture device is oriented according to said predetermined orientation, Preferably, when the symbol is viewed along a predetermined viewing axis, and when the capture device is at said predetermined distance, and when the capture device is oriented according to said predetermined orientation: The images are preferably acquired automatically, ie, without specific user intervention.

[0135] Preferably, the symbol changes appearance, for example color, or disappears when an image is captured under capture conditions associated with the symbol.

[0136] Second Main Aspect of the Invention The method according to the second main aspect of the invention comprises multiple cycles of steps a) to c).

[0137] In step b), an image capture device is used to capture an image, preferably a photograph, depicting an object in the user's mouth. In one embodiment, the image capture device is used to capture a video, and the captured image is extracted from the video.

[0138] In one embodiment, an "original mask", preferably a point cloud, is projected onto the observed scene in step a) by an acquisition device, preferably by a projector integrated in the acquisition device. A distorted mask resulting from the projection of the original mask then appears on the preview or equivalent image. In one embodiment, the projection is in infrared light so that the deformed mask is invisible to the naked eye. In one embodiment, the acquired image is an image representing the deformed mask. The acquisition device preferably uses an infrared camera. However, the nature of the deformed mask is not limited.

[0139] The images are preferably captured by the user themselves, who may capture the images using a mobile phone.

[0140] The images captured are preferably "extraoral," ie, the lenses of the capture device are not inserted into the user's mouth.

[0141] The image capture device may in particular be a mobile phone, a tablet, a camera or a computer, and the image capture device is preferably a mobile phone or a tablet so that the user can capture images anywhere, in particular outside the dental care professional's office, for example more than 1 km from the dental care professional's office.

[0142] In one embodiment, a user uses a mobile phone and a holder to which the mobile phone is removably attached, the holder being held relative to the user during the capture of at least some of the images, preferably all of the images. In particular, the holder may be of the type described in International Application No. PCT / EP2021 / 068702, European Patent Application Publication No. 17306361, International Application No. PCT / EP2019 / 079565, International Application No. PCT / EP2022 / 053847, French Patent Application Publication No. 2113577, French Patent Application Publication No. 2206750 or French Patent Application Publication No. 2206745.

[0143] In a preferred embodiment, the user uses a mobile phone whose position and orientation can be freely determined, specifically a mobile phone that is not attached to a holder. Indeed, the method described in this invention allows the user to be guided when taking images, so guidance by a holder is not necessary. Preferably, the image capture device does not come into contact with the user's mouth, either directly or through the image capture device holder.

[0144] Depending on the target, the computer or acquisition device may prompt the user to start or stop using an orthodontic appliance, such as an orthodontic aligner, cleats, or archwire appliance, in advance. Alternatively, the user may be asked to move their lips away from their dental arch, preferably using a retractor, to better expose the target to the image acquisition device, for example, to fully expose the outer surface of at least one tooth, particularly an incisor tooth, and / or to at least partially expose the outer surface of a molar tooth. Alternatively, the user may be asked to open their mouth wide to acquire an occlusal image showing the lingual and occlusal surfaces of the teeth and palate.

[0145] The number of images acquired in step a) is preferably less than 100, preferably less than 50, most preferably less than 10 so that the guide information can be updated quickly.

[0146] Before implementing the first step a) of the method according to the invention, the coverage level is zero.

[0147] In step b), the coverage level is updated to take into account the image acquired in the previous step a), or "new image".

[0148] In step b), the computer analyzes each new image, preferably according to the following steps: b1) determining the potential contribution of new images; b2) determining the intersection between the potential contribution and the previous contribution from the previously analyzed image; b3) if the intersection is not empty, adding the potential contribution to the previous contribution;

[0149] In step b1), the computer determines the potential contribution of the new image. Specifically, it determines whether the new image at least partially represents the target. If not, the new image cannot contribute and the computer proceeds to analyze the next new image. If yes, the computer determines the potential contribution of the new image, for example, the outline of the target representation on the new image or the number of target teeth at least partially represented in the new image.

[0150] In step b2), the computer then compares the potential contributions with a set of contributions resulting from the analysis of previously analyzed images, or "prior contributions".

[0151] For example, the potential contribution of a new image is the representation of the target in the new image, and the computer evaluates the intersection between this potential contribution and the previous contribution, which is made up of the sum of all representations of the target on previously analyzed images.

[0152] If this intersection is empty, the new image cannot make a new contribution and the computer proceeds to analyze the next new image. If this intersection is not empty, i.e., if the new image represents a region of the target that was not in any of the previously analyzed images, the computer adds the new contribution consisting of the intersection to the previous contribution.

[0153] In another example, the potential contribution of a new image is the number of one or more target teeth identified in the new image. The computer evaluates the intersection between this potential contribution and the previous contribution, which consists of the set of target tooth numbers identified in the previously analyzed image. If this intersection is empty, the new image cannot make a further contribution, and the computer proceeds to analyze the next new image. If this intersection is not empty, the computer adds it to the previous contribution.

[0154] The potential contribution of a new image may be determined by any known means.

[0155] In one embodiment, this involves segmenting the new image to identify any full or partial representation of the target. The analysis can be performed using conventional segmentation methods.

[0156] In particular, the new image may be submitted to a neural network trained to detect the representation of targets on the new image and to determine, for example, the number of teeth represented in the image, and / or the contours of those teeth, and / or the contours of the mouth, and / or the contours of the lips, and / or the contours of the tongue, as described, for example, in European Patent Application No. 18 184477.0.

[0157] Networks specialized for locating and detecting objects in images are well known. Neural networks include object detection networks, such as R-CNN (2013), SSD (Single Shot MultiBox Detector: Object Detection network), Faster R-CNN (Faster Region-based Convolutional Network method: Object Detection network), Faster R-CNN (2015), SSD (2015), RCF (Richer Convolutional Features for Edge Detection) (2017), SPP-Net (2014), OverFeat (Sermanet et al.) (2013), GoogleNet (Szegedy et al.) (2015), VGGNet (Simonyan and Zisserman) (2014), R-CNN (Girshick et al.) (2014), Fast R-CNN (Girshick et al.) (2015), ResNet (He et al.) (2016), and Faster R-CNN (Ren et al.) (2016), FPN (Lin et al.) (2016), YOLO (Redmon et al.) (2016), SSD (Liu et al.) (2016), ResNet v2 (He et al.) (2016), R-FCN (Dai et al.) (2016), ResNeXt (Lin et al. al.) (2017), DenseNet (Huang et al.) (2017), DPN (Chen et al.) (2017), YOL09000 (Redmon and Farhadi) (2017), Hourglass (Newell et al.) (2016), MobileNet (Howard et al.) (2017), DCN (Dai et al. al.) (2017), RetinaNet (Lin et al.) (2017), Mask R-CNN (He et al. al.) (2017), RefineDet (Zhang et al.) (2018), Cascade RCNN (Cai et al.) (2018), NASNet (Zoph et al.)(2019), CornerNet(Law and Deng)(2018), FSAF(Zhu et al.)(2019), SENet(Hu et al.)(2018), ExtremeNet(Zhou et al.)(2019), NAS-FPN(Ghiasi et al.)(2019), Detnas(Chen et al.)(2019), FCOS(Tian et al. (2019), CenterNet (Duan et al.) (2019), EfficientNet (Tan and Le) (2019), and AlexNet (Krizhevsky et al.) (2012). .

[0158] The above list is not exhaustive. For example, a neural network can learn from 1000 previous images, As input, a past image representing a past target, and As output, the neural network is trained by presenting representations of the target on past images.

[0159] Thus, the neural network learns to recognize the target representation in new images.

[0160] When the intersection between potential and previous contributions involves a comparison of the representation of the target in the new image and previously analyzed images, these representations are preferably projected onto a common reference model to take into account different acquisition conditions, in particular the orientation of the acquisition device, which varies according to the image under consideration.

[0161] The reference model preferably represents a reference object in the mouth that is similar or even identical to the object in the user's mouth.

[0162] To project the image, the computer analyzes the image to determine its capture conditions, i.e., the actual capture conditions, Specifically, the computer evaluates the distance between the capture device and the object in the user's mouth and the orientation in space of the capture device relative to the object in the user's mouth at the time of image capture.

[0163] Determining the actual acquisition conditions can be performed, for example, as described in European Patent Application No. 18 184477.0 or WO 2016 / 066651, or by subjecting the images to a neural network trained to determine the acquisition conditions of images submitted to the neural network.

[0164] The actual acquisition conditions are then virtually recreated in relation to the reference model, and a target representation of the user in the image is projected onto the reference model.

[0165] The projected surface set obtained from the previous image may constitute the previous contribution, and the projected surface obtained from the new image is the potential contribution.

[0166] Preferably, each image is submitted to a first detection neural network to identify intra-oral objects represented in the image, in particular the tongue and / or number of teeth and / or gums and / or mouth and / or lips and / or points of interest in these organs, and then each image is submitted to a second neural network trained to determine the acquisition conditions for the image to which it is submitted. Preferably, the second neural network receives as input the intra-oral objects detected by the first neural network, which improves the determination of the acquisition conditions.

[0167] In one embodiment, the potential contribution of a new image is determined by comparing the image with a "reference" image, e.g., a photograph or panoramic shot, of at least one dental arch that is preferably similar or identical to the user's dental arch.

[0168] In this case, the target will generally not be represented the same way on the reference image and on the new image. Preferably, a neural network is trained to match objects represented in the two images.

[0169] For example, it can be trained by presenting the following: a past record, each of which includes, as input, past images representing past targets under possible acquisition conditions by the acquisition device and an identification of a representation of the past target in the past image; and As an output, the identification of the historical target on the historical reference image.

[0170] Thus, the neural network learns to recognize target representations in reference images that correspond to target representations in new images presented to it, and thus, the neural network learns to identify the potential contributions of new images.

[0171] The method may be repeated several times, using a new reference image each time.

[0172] In step b3), the computer adds the potential contribution to the previous contribution if the intersection is not empty and calculates the coverage level resulting from the increment of the previous contribution by the new contribution.

[0173] In a preferred embodiment, the computer evaluates the quality of the acquired images and only adds potential contributions in step b3) if the quality is above a predetermined quality threshold. In particular, the quality may be an assessment of the sharpness and / or contrast and / or color balance of the image and / or the distance between the acquisition device and the user's mouth. Advantageously, only images of satisfactory quality are taken into account.

[0174] In one embodiment, the image capture device, preferably in the form of a mobile phone, is mounted in a holder that is held in contact with the user during capture, as described above, for example a holder of the type described in International Application No. PCT / EP2021 / 068702, European Patent Application No. 17306361, International Application No. PCT / EP2019 / 079565, International Application No. PCT / EP2022 / 053847, French Patent Application No. 2113577, French Patent Application No. 2206750 or French Patent Application No. 2206745. With such a holder, image quality (in particular brightness, distance of the capture device from the target, angle of the capture device relative to the target and orientation of the capture device about its optical axis) is advantageously well controlled, so that assessment of the quality of the captured image is optional.

[0175] Preferably, the holder cannot be bitten by the user, and even more preferably, allows for opening and closing of the arches (to a position where the arches touch each other in the occlusal plane).

[0176] A quality assessment is particularly advantageous when such a holder does not exist.

[0177] Depending on the results, the computer may decide to take several images, for example varying the focal length to get a first clear image of the incisors and then a second clear image of the molars.

[0178] The acquisition of several images with different calibration conditions may be programmed to be routine at each acquisition stage, which may be based on a quality assessment.

[0179] In step c), the computer compares the coverage level with a coverage threshold. If the coverage level is equal to or greater than the coverage threshold, step c) is complete. Alternatively, in the next step a), the computer determines guide information that guides the user to position the image capture device toward "future" capture conditions suitable for capturing additional images that increase the coverage level.

[0180] Thus, the guide information is determined to inform the user of the target area where the user still needs to acquire one or more images, and is presented to the user to guide the user to orient and / or position the image acquisition device according to the future acquisition conditions to be adopted for the next step a).

[0181] In a preferred embodiment, the computer determines future acquisition conditions for the next cycle, for example by random search or using an optimization algorithm, so that image acquisition under these future acquisition conditions maximizes the increase in coverage level.

[0182] The presentation of the guide information may include visual, tactile, and particularly tactile, communication of the guide information.

[0183] For example, the guide information may include voice commands instructing the user to move the image capture device toward or away from the teeth, to shift the image capture device to the right or left, to rotate the image capture device around the dental arch, to open and close the mouth, or to open and close the jaw.

[0184] The tactile transmission of the guide information can be, for example, a vibration that indicates to the user to stop moving.

[0185] The tactile transmission of guide information can be, for example, a vibration to indicate successful passage of a fiducial mark on the surface of a target or symbol.

[0186] The presentation of the guide information can be adapted to the user.

[0187] Preferably, the presentation of guide information includes several different types of communication that stimulate several different senses, thus facilitating communication to the user.

[0188] Preferably, the guide information is presented on a screen, preferably on a screen of the image capture device. a reference frame that preferably allows the user to orient themselves when moving the acquisition device in space, i.e. to assess how the acquisition device is positioned relative to the object in the mouth, and in particular relative to the target; - an indicator of movement relative to this frame of reference.

[0189] The reference frame preferably at least partially represents at least one object in the mouth as observed by the acquisition device in a symbolic or realistic manner (adapted to a user's recognition of the represented object), which is determined according to the actual acquisition conditions of the acquisition device.

[0190] The reference frame can be, for example, a preview image, which is an image observed in real time by an acquisition device, preferably a mobile phone, and displayed on the screen of the acquisition device, and / or an equivalent image representing a part of the user, for example the user's head or part of the head, or the user's mouth or dental arch ("equivalent" means that the image corresponds to an observation of a part of the patient that can be superimposed on the image observed by the acquisition device, specifically the image observed along the optical axis of the acquisition device).

[0191] The equivalent image may be, for example, a line drawing depicting the outline of a portion of the user.

[0192] The reference frame may represent a view of a user-specific model or a generic model, such that the model represents precisely or more coarsely a part of the user, preferably at least a target, preferably at least an object in the mouth.

[0193] The generic model is common to multiple individuals. Specifically, the generic frame of reference may be determined by statistical analysis of historical data representing these individuals. The generic model may be, for example, a typodont model.

[0194] The user-specific model may be a model of all or part of an object in the user's mouth, specifically a model of the user's target. Specifically, it may be a scan of the user's dental arch. It may also include or be a 3D model of the user's dental arch in a configuration specific to a treatment stage. Specifically, it may include or be a 3D model of the user's dental arch in a configuration suitable for a treatment stage with orthodontic aligners, specifically a 3D model used in the design and manufacture of orthodontic aligners. Such a 3D model may be generated at the start of or during orthodontic treatment.

[0195] The equivalent image is preferably a generic or specific view of the model. Preferably, a texture is applied to the model to make it more realistic and easier for the user to identify with the model. The texture may be extracted from an image, for example the image acquired in step a), and then applied to the model, preferably selected from the database before step a).

[0196] The model to which the view is used as reference may in particular be the reference model used as a projection medium for the acquired images, as explained above.

[0197] The equivalent image may be at least partially symbolic: it may, for example, comprise a set of geometric shapes representing intra-oral objects, e.g., a set of discs, each disc representing a tooth of a dental arch, the intra-oral objects being the dental arch.

[0198] 10 shows two examples of equivalent images, representing views of a 3D model of a user's arch with and without gums, respectively. The views may be, for example, wireframe representations.

[0199] In particular, if the equivalent image is a view of a generic or specific model, the image capture device can display a preview image, preferably in a "thumbnail" window, which facilitates spatial location for the user.

[0200] Displaying the reference frame on the screen is optional, provided that the indicator provides an indication of the desired movement. For example, the indicator may be an arrow or a message recommending a particular movement. However, displaying the reference frame on the screen is preferred, as it significantly facilitates precise positioning of the acquisition device.

[0201] The indicator, preferably together with the reference frame, is displayed on a screen, preferably on the screen of an image capture device, preferably on a mobile phone or tablet screen.

[0202] In a preferred embodiment, the reference frame includes a representation of the intra-oral object, and the indicator is a mark that indicates an area of ​​this representation that has not yet been covered. The indicator can be, for example, a special outline surrounding this area, or preferably a special color applied to this area, or a symbol superimposed on this area. The "special" outline or color allows the user to distinguish this area from the rest of the representation of the intra-oral object.

[0203] This display helps guide the user quickly and efficiently. The guidance system, which gives the user great freedom, is intuitive and therefore does not require prior training to be guided.

[0204] In particular, the indicators may be displayed transparently or highlighted on the representation of the objects in the mouth.

[0205] The indicator is preferably displayed in augmented reality when the reference frame is a preview image or equivalent.

[0206] Coverage Rate and Threshold Preferably, in step c) the user is informed, preferably in real time, of the coverage level achieved, ie the progress of the acquisition, and preferably of the coverage threshold.

[0207] Preferably, the coverage level information and / or coverage threshold information is presented on a screen, preferably on the user's mobile phone screen. The information may take the form of a meter or gauge, for example a progress bar.

[0208] In a preferred embodiment, the coverage levels and / or coverage thresholds are represented "graphically" on the screen, in particular in the form of lines and / or areas and / or symbols.

[0209] In one embodiment, the screen comprises: - the initial area to be covered, and - the covered area, Preferably, a representation of elements of the target context is displayed, e.g., parts of intraoral objects other than the target, i.e. parts of intraoral objects that the method is not intended to cover, e.g., teeth adjacent to the tooth whose image is being acquired.

[0210] For example, when the reference frame is a symbolic or preferably realistic representation of the mouth or object within the target, the initial area to be covered can be presented on the screen in a way that can be identified by the user, in order to inform the user of the coverage threshold. In particular, it can be colored with a particular color, or more generally, can be represented by a particular appearance or can be delimited by a particular outline. Thus, the area represented by the particular appearance or enclosed by this outline represents the coverage threshold.

[0211] Similarly, the covered area, i.e., the area for which at least one image has already been acquired, can be presented on the screen in a way that can be identified by the user, in order to inform the user of the coverage level. In particular, it can be colored with a particular color, or more generally, it can be represented by a particular appearance or be delimited by a particular outline. Thus, an area represented by a particular appearance or surrounded by this outline represents a coverage level.

[0212] For example, a target surface may be displayed in green or red depending on whether acquisition of this surface is complete or whether acquisition of this surface is still to be performed. Covered areas may be displayed transparent or highlighted.

[0213] In one embodiment, the coverage threshold is graphically represented as a set of symbols displayed adjacent to, and preferably superimposed on, a representation of each set of teeth. These tooth representations belong to, or even constitute, the reference frame. For example, the symbols may be presented in augmented reality on a preview image of a mobile phone or on a view of a dental arch model, preferably on a view of the user's dental arch model. The appearance of the symbols for teeth for which desired images have already been acquired ("covered teeth") may be different from the appearance of the symbols for teeth for which all desired images have not yet been acquired ("teeth still to be covered"), allowing the coverage rate to be seen graphically.

[0214] In one embodiment, the tooth symbols disappear as soon as the tooth is covered. The user then sees the difference between the coverage threshold (all symbols initially displayed) and the coverage level (missing symbols).

[0215] The "graphical" display of coverage thresholds and coverage levels is particularly effective in ensuring that the user acquires all images required.

[0216] Notably, the graphical representations of the coverage threshold and coverage level indicate areas of the target that still need to be covered, i.e., areas where the desired image is still to be acquired. These graphical representations can be used as indicators to guide the user. For example, coloring the covered areas in a different color from the areas that still need to be covered highlights the areas that still need to be covered, thus guiding the user.

[0217] The graphic or "visual" marking of the initial area to be covered, the covered area, or the area yet to be covered is not limited to the application of color, texture, shape, or a particular symbolic representation.

[0218] Preferably, the graphical representation of the coverage thresholds and coverage levels is displayed in augmented reality, preferably on a mobile phone screen.

[0219] In one embodiment, a stopwatch is started to measure the duration of image acquisition since the first step a), and displaying this time and the coverage level and / or the difference between the coverage threshold and the coverage level is a motivating factor for the user.

[0220] In one embodiment, the score is calculated as a function of the time taken to reach the coverage threshold, and / or the quality of the acquired images, and / or the usefulness of the acquired images, or more generally, the goals set by the user.

[0221] In one embodiment, the initial area to be covered includes regions that have been assigned utility factors, and the score is determined as a function of the utility factors of the regions within the covered area. For example, in one embodiment, the initial surface to be covered may be composed of a portion that is mandatory to cover and a portion that is optional to cover. The utility factor assigned to pixels in the "mandatory" section may be, for example, 100, and the utility factor assigned to pixels in the "optional" section may be, for example, 10. The score may be, for example, a function or even the sum of the utility factors for all pixels within the covered area.

[0222] The score may be compared to scores previously achieved by the user or other users to obtain a ranking of the set of image acquisition operations.

[0223] Rankings may be established for several patients, for example for all patients of the same doctor. Informational messages and / or gifts, such as rewards, may be sent to patients according to their ranking order.

[0224] The stopwatch and / or scores and / or rankings may be displayed on the acquisition device screen.

[0225] This makes acquisition fun: specifically, acquisition may be presented as a video game, with the objective being to reach the coverage threshold as quickly as possible.

[0226] Guided by the guide information and motivated by the coverage level information, the user modifies the acquisition conditions, allowing a new step a) to be resumed, preferably immediately upon the end of step c).

[0227] Once the coverage levels are presented to the user, the user can instantly visualize the effect of moving the acquisition device, specifically when targets become stained or when symbols associated with teeth change appearance or disappear as image acquisition progresses. The guide is very intuitive.

[0228] In a preferred embodiment, the screen displays a realistic representation of the intra-oral objects and surfaces currently covered. The covered areas are completed as the cycle progresses, allowing the user to easily identify areas still to be acquired and position and orient the image capture device accordingly.

[0229] The time interval between two successive cycles of steps a)-c) is preferably 5 minutes, 1 minute, 30 seconds, or less than 1 second. Preferably, the user acquires the acquired images in real time, preferably by photographing the object in the mouth, and steps b)-c) are performed immediately for each acquired image.

[0230] At the end of the cycle of steps a) to c), ie when the coverage level is equal to or greater than the coverage threshold, the acquired images may be transmitted to the user and / or preferably to a dental care professional.

[0231] The acquired images may be stored, for example, in a database that is preferably accessible to dental professionals and / or users, for example, the acquired images may be stored in the user's medical file.

[0232] The acquired image set typically includes more than 2, more than 5, more than 10, more than 50, more than 100, and / or less than 10,000 images.

[0233] Specifically, the acquired image set includes: -To assess the user's dental condition before, during, or after orthodontic or dental treatment; and / or - to generate or correct a model of the user's dental arch; and / or -to design orthotics, and / or -Can be used to design and recommend dental treatments such as dental hygiene, periodontal treatment, or whitening.

[0234] In certain embodiments, at the end of the cycle of steps a)-c), the method may involve analyzing the acquired images to generate a model of the target, referred to as a "final model." The final model may be sent to a user, preferably a dental care professional. The final model may depict the target with high accuracy. The final model may be generated by the dental care professional's computer to which the acquired images are sent, or by an image acquisition device. The final model may be stored, for example, in a database preferably accessible to the dental care professional and / or the user. For example, the final model may be stored in the user's medical file. [Example]

[0235] The objective of the acquisition is to obtain a target image set consisting of, for example, all of the user's teeth. The intraoral object is made up of a dental arch, including the teeth and gums. The intraoral object is modeled in the form of a computer-accessible reference model 16. The reference model 16 may originate from a database and may be generic. Targets are identified on the reference model. Thus, the initial area to be covered is the target area within the reference model.

[0236] Figures 3, 5, 6 and 7 show an example of the first main aspect of the present invention, where a multidimensional symbol 24 is virtually positioned in space to guide a user to relevant acquisition conditions.

[0237] In the example shown in FIG. 3, the symbols 24 are two-dimensional. They each take the form of three concentric, coplanar rings. They are represented on a view of a reference model representing the arch, which view the acquisition device observes when observing the user's dental arch. The view is preferably presented on the screen of the phone used for acquisition. The user's aim is to position the phone so that the target is viewed head-on, i.e., so that the rings appear circular. The optical axis is then aligned with a predetermined observation axis suitable for image acquisition.

[0238] No fiducial marks are required for this guide, however, fiducial marks representing, for example, the circular outline of the ring when viewed from the front, will improve the positioning accuracy of the acquisition device.

[0239] In the example shown in Figure 5, the symbols are three-dimensional. They each take the form of three concentric superimposed rings. They are represented on a view of a reference model representing the arch, which the acquisition device observes when observing the user's dental arch. The view is preferably presented on the screen of the phone used for acquisition. The user's goal is to position the phone so that the target is viewed head-on, as in Figure 6, i.e., so that the rings appear circular and concentric. The optical axis is then aligned with the predetermined observation axis suitable for image acquisition, i.e., the X-axis of the rings.

[0240] In the example shown in Figure 7, each symbol 24 is composed of two concentric hoops extending in planes at 90° to each other. The two hoops are preferably of the same shape (same inner and outer diameters) and are preferably surrounded by a spherical color 26, but are transparent to facilitate their location. The intersection of the two planes defines a predetermined observation axis X associated with the symbol that is identifiable by the user. This form of the symbol makes it very easy to determine how to move the acquisition device.

[0241] In the embodiment shown in FIG. 7, a first horizontal hoop is used to determine whether the acquisition device should be moved up or down, and a second vertical hoop is used to determine whether the acquisition device should be moved to the right or left in a plane passing through the center of the mouth.

[0242] The three-dimensional symbology guide is particularly effective: no fiducial marks are required to precisely position the optical axis of the acquisition device along a predetermined viewing axis suitable for image acquisition.

[0243] The three-dimensional symbol is also used to guide the capture device to a predetermined distance along a predetermined observation axis. In the example shown in Fig. 8, the distance d between the rings represents the distance between the capture device and the symbol along the X axis of the symbol, i.e., along the predetermined observation axis. The predetermined distance may, for example, correspond to a view of the symbol where the rings touch (d = 0). It is easy for the user to move the capture device to this position.

[0244] When a predetermined capture condition associated with the symbol is reached, the image is preferably captured automatically and the appearance of the symbol, for example color, is preferably modified or the symbol disappears.

[0245] An example illustrating the second main aspect of the present invention will now be described. In step a), an image is acquired using an acquisition device. In step b), the acquired images are analyzed to update the coverage level.

[0246] Specifically, it looks for possible representations of the target on the acquired image, i.e., the presence of potential contributions from the acquired image.

[0247] If this potential contribution exists, a search is made for the view of the reference model showing the greatest match with the acquired image, from which the area of ​​that view corresponding to the target and, consequently, the corresponding zone on the reference model are estimated. If a part of the latter's surface is not already registered as belonging to the covered area, it is added to the covered area and marked on the reference model, preferably colored in a first color specific to the covered area, for example green, the remaining part of the target's area on that view preferably colored in a second color, for example red, and the area of ​​the reference model not defining the target preferably colored in a third different color, for example white.

[0248] A view of the reference model 16 corresponding to the preview image is projected in the direction of the optical axis onto the screen of the image capture device 10, preferably a mobile phone.

[0249] The projected view of the reference model is - be almost exactly superimposed on the preview image displayed on the screen, whether transparent or not, or - The preview image may be replaced as shown in Figure 4.

[0250] It allows the user to see, thanks to their particular color, which areas have been covered and which areas have not yet been acquired.

[0251] This presentation allows the user to quickly and easily identify areas of the tooth that have not yet been covered and easily orient the acquisition device accordingly, and also informs the user of the coverage level.

[0252] As images are acquired during the cycle of steps a)-c), the area covered increases.

[0253] The images in FIG. 4 each show a view of a reference model representing two dental arches, preferably similar to the user's dental arch. Each view corresponds to a preview image and is displayed in place of the preview image, preferably on the screen of the mobile phone used for image acquisition. The reference model views are therefore "equivalent" to the preview image. In other words, as the user rotates the acquisition device around the user's mouth, the displayed reference model views instantly adapt accordingly. Thus, the user can easily assimilate the reference model to the user's dental arch. Thus, the user can easily position and orient the acquisition device to acquire images of teeth that have not yet been covered.

[0254] In the embodiment shown in Figure 4, the target consists of all teeth on both arches, and the intra-oral objects consist of both arches (thus including gums and teeth). The tooth color is specifically dark gray (GF) if tooth coverage is sufficient, and light gray (GS) if not.

[0255] As the user moves the acquisition device in front of the user's teeth, the surface area covered increases, and therefore the number of well-covered teeth shown in dark grey increases, while other teeth remain light grey.

[0256] The coverage level corresponds to, for example, the percentage of the covered area relative to the initial area to be covered. The coverage threshold can be the percentage of the target area to be covered. For example, the threshold can be 90%, i.e., the coverage threshold is reached when more than 90% of the tooth surface belongs to the covered area.

[0257] A one-dimensional symbol in the form of a dot may symbolically represent the tooth (target) to be covered. For example, once at least 90% of the tooth surface has been acquired, or better yet, once at least 95% of the tooth surface has been covered, or even better, once the entire tooth surface has been covered, the symbol symbolically representing this tooth is no longer shown on the screen. Alternatively, the symbol may be displayed in color or in a contrasting manner.

[0258] As is now apparent, devices and methods according to the present invention advantageously increase user autonomy and allow for improved quality and content of images acquired by a user without specific knowledge in the dental field. They can also be used to generate, from a distance, 3D models of targets belonging to or constituting objects in the user's mouth. Finally, they make it much easier for a user to decide on and track any orthodontic treatment remotely, without the need to make an appointment with a dental professional.

[0259] Naturally, the present invention is not limited to the embodiments described and illustrated above.

[0260] In particular, a mobile phone can be replaced by a device equipped with a camera and comprising a holder held against the user during acquisition of an image set, and a screen displaying the scene observed by the camera, the screen being integrated into the holder or at a distance from the holder.

[0261] The shape of the symbols is not limited: one-dimensional, two-dimensional, or three-dimensional symbols can be presented simultaneously in augmented reality.

Claims

1. 1. A method for acquiring a set of images covering targets belonging to objects in a user's mouth, the method comprising: presenting to the user on a screen (12) and using spatial augmented reality with respect to the object in the mouth observed by the image capture device (10), a multidimensional symbol or a set of multidimensional symbols (24), the shape and / or position of each symbol being determined to indicate to the user at least one predetermined capture condition suitable for capturing such an image; and for each symbol, capturing such an image using the capture device when at least one predetermined capture condition associated with the symbol is satisfied, preferably when all predetermined capture conditions associated with the symbol are satisfied.

2. 2. The method of claim 1, wherein in step 2), an image is captured using the capture device only if a predetermined capture condition associated with at least one symbol is met.

3. At least one symbol (24) is a symbol axis (X), preferably a rotation axis, wherein the acquisition condition is an angular deviation between the optical axis of the acquisition device and the symbol axis of less than 20°, and / or A method according to claim 1 or 2, in which a dimension (d) is defined on the representation of the symbol on the screen that is variable as a function of the distance between the acquisition device and the symbol in augmented reality, the acquisition condition being a specific value for the dimension or the attribution of the dimension to a predetermined specific range of values.

4. 4. The method according to claim 1, wherein in step 2) the images are automatically acquired using the acquisition device if predetermined acquisition conditions are met, the acquisition conditions defining the position in space of the acquisition device and / or its orientation around its optical axis and including the at least one acquisition condition indicated by the symbol.

5. In step 2), such an image is acquired using the acquisition device, - the appearance of the symbol is modified or the symbol is erased, and / or - an audible signal is emitted, and / or A method according to any one of claims 1 to 4, wherein a score is modified which is displayed on a screen and which is related to the coverage rate of the target by the already acquired images, and / or related to the duration for the acquisition of the already acquired images, and / or related to the quality of the already acquired images, and / or related to the usefulness of the already acquired images.

6. The method of claim 5 , wherein a ranking determined as a function of the scores is presented to the user on the screen when the image sets are acquired.

7. 7. The method of claim 1, wherein the screen displays the symbol on a preview image representing the real scene observed by the acquisition device, or on a view of a model representing at least the object or target in the mouth, such as the preview image.

8. 8. A method according to any one of claims 1 to 7, wherein the screen displays a reference mark at a fixed position on the screen, such symbol preferably having a shape complementary to the reference mark when a predetermined acquisition condition associated with said symbol is met.

9. The method of any one of claims 1 to 8, wherein the target comprises more than five teeth and / or orthodontic appliances and / or the symbol set comprises more than two symbols.

10. The method according to any one of claims 1 to 9, wherein the acquisition device is operated by the user in steps 1) and 2).

11. Acquisition method according to any one of claims 1 to 10, wherein said image is preferably a realistic photograph and / or represents a deformed mask resulting from the projection, by said acquisition device, of an original mask, preferably in the form of a grid or a set of dots.

12. A device for carrying out the method according to any one of claims 1 to 11, comprising: an image acquisition device, preferably in the form of a mobile phone (10); a computer (14), preferably integrated in or in communication with said acquisition device, having a computer program comprising program code instructions, said program code instructions comprising: - in step 1), placing and presenting to the user in augmented reality within the space of the oral object on a screen (12, 18), preferably on the screen (12) of the acquisition device, one or more multidimensional symbols (24), the shape and / or position of which is determined to indicate to the user at least one predetermined acquisition condition suitable for acquiring such an image; - preferably in step 2), the device is for allowing the acquisition device to acquire such an image only if said at least one predetermined acquisition condition associated with a symbol is fulfilled, and / or for instructing said acquisition device to acquire such an image only if said at least one predetermined acquisition condition is fulfilled, and / or for updating a coverage level of said target by acquired images, preferably for comparing said coverage level with a coverage threshold, and preferably for presenting information on said coverage level and / or information on the difference between said coverage threshold and said coverage level on said screen.

13. The acquisition device a mobile phone, said screen being integrated into said mobile phone, or The device of claim 12, comprising a holder equipped with a camera and held against the user during image capture, the screen being integrated into the holder or at a distance from the holder.

Images