Method, device, equipment and medium for detecting the clarity of pressed film of shell-shaped diaphragm

Abstract

The present application provides a kind of shell membrane sheet's press film definition detection method, device, equipment and medium, method includes: obtaining the image to be detected including the bottom surface of appliance assembly, appliance assembly includes light curing mold and shell membrane sheet formed on the outside of light curing mold by press film, shell membrane sheet forms the edge to be detected close to light curing mold at bottom surface;Obtain the gap between the first profile of the bottom outer contour corresponding to light curing mold and the second profile corresponding to the edge to be detected in the image to be detected;According to the gap, judge the press film definition of shell membrane sheet.The present application is based on the way of image recognition, obtains the first profile of the bottom outer contour corresponding to light curing mold and the second profile corresponding to the edge to be detected in the image to be detected, according to the gap between the first profile and the second profile, the press film definition can be more intuitively judged, the present application is based on the press film definition detection method of shell membrane sheet of vision, realizes the efficient identification of unclear press film.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of medical devices, in particular to a shell-shaped film sheet pressing film clarity detection method, device, equipment and medium. BACKGROUND

[0002] Due to the advantages of aesthetics, convenience and cleanliness, shell-shaped dental orthodontic appliances (such as invisible aligners) based on polymer materials are becoming more and more popular. Shell-shaped dental orthodontic appliances use the elastic force generated by deformation to reposition teeth from one layout to another.

[0003] The production process of shell-shaped dental orthodontic appliances (hereinafter referred to as aligners) usually needs to go through the following processes: photocuring mold forming -> pressing film on the aligner using the photocuring mold -> aligner cutting, unshelling -> aligner grinding, cleaning -> aligner sorting, packaging.

[0004] During the pressing film stage of the aligner, due to environmental factors and the influence of the pressing film machine parameters, the pressing film may not be clear. The aligner with unclear pressing film is a defective product, which is not conducive to wearing and thus affects the final treatment effect, and needs to be identified and feedback given when it occurs in large quantities to maintain the corresponding pressing film equipment.

[0005] The common pressing film clarity detection method at present mainly relies on visual inspection by operators and quality inspectors during production. However, the current detection method has the following problems:

[0006] (1) Due to the demand for production, the requirement for quality control and the number of personnel, visual inspection is very laborious, which brings a lot of work pressure to operators and quality inspectors;

[0007] (2) Visual inspection of the pressing film clarity is affected by subjective factors (such as vision, experience, fatigue level, etc.) of operators and quality inspectors, and cannot form an objective and unified evaluation standard, which is not conducive to quality control. SUMMARY

[0008] Aspects of the present application provide a shell-shaped film sheet pressing film clarity detection method, device, equipment and medium to effectively detect the pressing film clarity of the shell-shaped film sheet.

[0009] In an aspect of the present application, a shell-shaped film sheet pressing film clarity detection method is provided, comprising:

[0010] obtaining a to-be-detected image including the bottom surface of an aligner assembly, the aligner assembly comprising a photocuring mold and a shell-shaped film sheet formed on the outside of the photocuring mold, the shell-shaped film sheet forming a to-be-detected edge close to the photocuring mold at the bottom surface;

[0011] acquiring a gap between a first contour corresponding to the bottom outer contour of the light-cured mold and a second contour corresponding to the edge to be detected in the image to be detected;

[0012] judging the film pressing definition of the shell-shaped diaphragm according to the gap.

[0013] According to the aspect and any possible implementation manner described above, further provided is an implementation manner, and the step of "acquiring an image to be detected including the bottom surface of the appliance assembly" specifically comprises:

[0014] acquiring a bottom surface image of the appliance assembly;

[0015] performing target detection on the bottom surface image by using a pre-trained posterior tooth area target detection model;

[0016] in response to the posterior tooth area detected from the bottom surface image, cropping an image to be detected including the posterior tooth area from the bottom surface image.

[0017] According to the aspect and any possible implementation manner described above, further provided is an implementation manner, and the step of "cropping an image to be detected including the posterior tooth area from the bottom surface image" specifically comprises:

[0018] cropping two images to be detected respectively corresponding to two posterior tooth areas from the bottom surface image.

[0019] According to the aspect and any possible implementation manner described above, further provided is an implementation manner, and the step of "acquiring a gap between a first contour corresponding to the bottom outer contour of the light-cured mold and a second contour corresponding to the edge to be detected in the image to be detected" specifically comprises:

[0020] acquiring an average gap between the first contour corresponding to the bottom outer contour of the light-cured mold and the second contour corresponding to the edge to be detected in the image to be detected.

[0021] According to the aspect and any possible implementation manner described above, further provided is an implementation manner, and the step of "acquiring an average gap between the first contour corresponding to the bottom outer contour of the light-cured mold and the second contour corresponding to the edge to be detected in the image to be detected" specifically comprises:

[0022] acquiring the first contour corresponding to the bottom outer contour of the light-cured mold in the image to be detected;

[0023] acquiring the second contour corresponding to the edge to be detected in the image to be detected;

[0024] calculating the gap between each corresponding point between the first contour and the second contour;

[0025] An average gap is calculated by averaging a plurality of gaps.

[0026] According to the aspect and any possible implementation as above, there is further provided an implementation, wherein the step of "obtaining a first profile corresponding to the bottom outer contour of the light-cured mold in the image to be detected" specifically comprises:

[0027] A first mask showing the bottom outer contour of the light-cured mold is obtained according to the image to be detected;

[0028] An edge of the first mask is smoothed to obtain a second mask;

[0029] Non-connected regions inside the second mask are removed to obtain a third mask;

[0030] A first profile corresponding to the bottom outer contour of the light-cured mold is obtained according to the third mask.

[0031] According to the aspect and any possible implementation as above, there is further provided an implementation, wherein the step of "obtaining a second profile corresponding to the edge to be detected in the image to be detected" specifically comprises:

[0032] A plurality of target points are selected at intervals at the first profile;

[0033] A normal vector of each target point away from the light-cured mold is obtained;

[0034] A gray-scale gradient distribution curve of each target point along the corresponding normal vector is obtained;

[0035] A peak point of each gray-scale gradient distribution curve is obtained;

[0036] A plurality of peak points are connected to obtain a second profile corresponding to the edge to be detected.

[0037] According to the aspect and any possible implementation as above, there is further provided an implementation, wherein the step of "obtaining a gray-scale gradient distribution curve of each target point along the corresponding normal vector" specifically comprises:

[0038] A gray-scale distribution curve of each target point along the corresponding normal vector is obtained;

[0039] The gray-scale distribution curve is smoothed to obtain a smoothed gray-scale distribution curve;

[0040] The corresponding gray-scale gradient distribution curve is obtained according to the smoothed gray-scale distribution curve.

[0041] According to the aspect and any possible implementation as above, there is further provided an implementation, wherein the step of "obtaining a peak point of each gray-scale gradient distribution curve" specifically comprises:

[0042] The peak value points greater than the peak value threshold on each gray gradient distribution curve are obtained by using a peak searching algorithm.

[0043] As described above, the aspect and any possible implementation, further provides an implementation, the step "calculating the gap between each corresponding point of the first profile and the second profile" specifically includes:

[0044] The gap between each target point on the first profile and the corresponding peak value point is calculated.

[0045] As described above, the aspect and any possible implementation, further provides an implementation, the step "judging the press film clarity of the shell-shaped diaphragm according to the gap" specifically includes:

[0046] Judging the size of the average gap and the gap threshold value;

[0047] If not greater than, judging that the shell-shaped diaphragm is in the press film clear state;

[0048] If greater than, judging that the shell-shaped diaphragm is in the press film unclear state.

[0049] As described above, the aspect and any possible implementation, further provides an implementation, the step "obtaining the image to be detected including the bottom surface of the appliance assembly" specifically includes:

[0050] The bottom surface of the appliance assembly is image collected by adopting the way of shooting from the bottom, and the image to be detected including the bottom surface of the appliance assembly is obtained.

[0051] Another aspect of the application provides a shell-shaped diaphragm press film clarity detection device, comprising:

[0052] The first acquisition module is configured to obtain an image to be detected including a bottom surface of an appliance assembly, the appliance assembly comprising a light-cured mold and a shell-shaped diaphragm formed on the outside of the light-cured mold, the shell-shaped diaphragm forming a to-be-detected edge close to the light-cured mold at the bottom surface;

[0053] The second acquisition module is configured to obtain a gap between a first profile corresponding to the bottom outer profile of the light-cured mold and a second profile corresponding to the to-be-detected edge in the image to be detected.

[0054] The determination module is configured to judge the press film clarity of the shell-shaped diaphragm according to the gap.

[0055] As described above, the aspect and any possible implementation, further provides an implementation, the first acquisition module is specifically configured to:

[0056] Obtain the bottom surface image of the appliance assembly;

[0057] The apparatus further comprises:

[0058] a detection module configured to perform target detection on the bottom surface image by using a pre-trained posterior tooth area target detection model;

[0059] a cropping module configured to crop a to-be-detected image including a posterior tooth area from the bottom surface image in response to the posterior tooth area detected from the bottom surface image.

[0060] According to the aspect and any possible implementation manner as described above, further provided is an implementation manner, and the cropping module is specifically configured to crop two to-be-detected images respectively corresponding to two posterior tooth areas from the bottom surface image.

[0061] According to the aspect and any possible implementation manner as described above, further provided is an implementation manner, and the second acquisition module is specifically configured to:

[0062] acquire an average gap between a first contour corresponding to a bottom outer contour of the light-cured mold and a second contour corresponding to the to-be-detected edge in the to-be-detected image.

[0063] According to the aspect and any possible implementation manner as described above, further provided is an implementation manner, and the second acquisition module is specifically configured to:

[0064] acquire a first contour corresponding to a bottom outer contour of the light-cured mold in the to-be-detected image; and acquire a second contour corresponding to the to-be-detected edge in the to-be-detected image.

[0065] The apparatus further comprises:

[0066] a calculation module configured to calculate a gap between each corresponding point of the first contour and the second contour; and calculate an average value of a plurality of gaps to obtain an average gap.

[0067] According to the aspect and any possible implementation manner as described above, further provided is an implementation manner, and the second acquisition module is specifically configured to:

[0068] acquire a first mask showing the bottom outer contour of the light-cured mold according to the to-be-detected image;

[0069] smooth an edge of the first mask to obtain a second mask;

[0070] remove a non-connected area inside the second mask to obtain a third mask;

[0071] acquire a first contour corresponding to the bottom outer contour of the light-cured mold according to the third mask.

[0072] In the aspect and any possible implementation ways as above, further provided is an implementation way, the second acquisition module is specifically used for:

[0073] selecting a plurality of target points distributed at intervals at the first contour;

[0074] acquiring a normal vector of each target point away from the light-cured mold;

[0075] acquiring a gray scale gradient distribution curve of each target point along the corresponding normal vector;

[0076] acquiring a peak point of each gray scale gradient distribution curve;

[0077] connecting a plurality of peak points to obtain a second contour corresponding to the edge to be detected.

[0078] In the aspect and any possible implementation ways as above, further provided is an implementation way, the second acquisition module is specifically used for:

[0079] acquiring a gray scale distribution curve of each target point along the corresponding normal vector;

[0080] smoothing the gray scale distribution curve to obtain a smoothed gray scale distribution curve;

[0081] obtaining a corresponding gray scale gradient distribution curve according to the smoothed gray scale distribution curve.

[0082] In the aspect and any possible implementation ways as above, further provided is an implementation way, the second acquisition module is specifically used for:

[0083] acquiring a peak point greater than a peak threshold on each gray scale gradient distribution curve by using a peak searching algorithm.

[0084] In the aspect and any possible implementation ways as above, further provided is an implementation way, the calculation module is specifically used for:

[0085] calculating a gap between each target point on the first contour and the corresponding peak point.

[0086] In the aspect and any possible implementation ways as above, further provided is an implementation way, the determination module is specifically used for:

[0087] judging the size of the average gap and a gap threshold;

[0088] if not greater than, judging that the shell-shaped diaphragm is in a clear state of film pressing;

[0089] if greater than, judging that the shell-shaped diaphragm is in an unclear state of film pressing.

[0090] According to the aspect and any possible implementation manner described above, further provided is an implementation manner, the first acquisition module is specifically configured to:

[0091] An image of the bottom surface of the appliance assembly is captured by taking a photograph from a bottom view to obtain the to-be-detected image including the bottom surface of the appliance assembly.

[0092] According to another aspect of the present application, a device is provided, the device comprising:

[0093] one or more processors;

[0094] a storage device configured to store one or more programs,

[0095] when the one or more programs are executed by the one or more processors, the one or more processors implement the method provided by the aspect described above.

[0096] According to another aspect of the present application, a computer readable storage medium is provided, the computer readable storage medium stores a computer program, the computer program is executed by a processor to implement the method provided by the aspect described above.

[0097] According to the technical solution described above, the first profile of the bottom outer contour of the light-cured mold and the second profile of the to-be-detected edge in the to-be-detected image can be obtained based on the image recognition manner in an embodiment of the present application. The gap between the first profile and the second profile can be obtained by calculation, and the gap can be used to more intuitively judge the film pressing clarity. The shell-shaped film piece pressing mold clarity detection method based on vision in the embodiment realizes efficient identification of unclear pressing molds, thereby obtaining the following advantages: (1) the computer and related vision hardware are used to efficiently complete the pressing mold clarity judgment, thereby reducing the work load of the operating workers and quality inspection personnel, improving the production efficiency, and assisting in the capacity improvement; (2) the judgment standard based on the gap is more objective and unified, effectively controls the product quality, and is helpful to form a perfect quality traceability and related feedback mechanism; (3) the detection efficiency is high, the speed is fast, the labor cost is low, and the detection accuracy is high, and the method is reliable in the complex production environment. BRIEF DESCRIPTION OF DRAWINGS

[0098] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor.

[0099] Figure 1 A flowchart of the shell-shaped film piece pressing mold clarity detection method provided by an embodiment of the present application is shown in the figure.

[0100] Figure 2 is a schematic diagram of the bottom surface of an orthodontic appliance assembly according to an embodiment of the present invention;

[0101] Figure 3 2 is a schematic diagram of a target detection frame selecting a posterior tooth area in a bottom surface image according to an embodiment of the present invention;

[0102] Figure 4 is a schematic diagram of a cropped image to be detected according to an embodiment of the present invention;

[0103] Figure 5 is a schematic diagram of a first mask according to an embodiment of the present invention;

[0104] Figure 6 is a schematic diagram of a second mask according to an embodiment of the present invention;

[0105] Figure 7 is a schematic diagram of a second mask having a first edge according to an embodiment of the present invention;

[0106] Figure 8 is a schematic diagram of a third mask according to an embodiment of the present invention;

[0107] Figure 9 is a schematic diagram of a plurality of target points and normal vectors located at a first contour according to an embodiment of the present invention;

[0108] Figure 10 is a schematic diagram of a grayscale distribution curve according to an embodiment of the present invention;

[0109] Figure 11 is a schematic diagram of a smoothed grayscale distribution curve according to an embodiment of the present invention;

[0110] Figure 12 is a schematic diagram of a grayscale gradient distribution curve according to an embodiment of the present invention;

[0111] Figure 13 is a schematic diagram of a second profile obtained according to an embodiment of the present invention;

[0112] Figure 14 is a graph of average gap according to an embodiment of the present invention;

[0113] Figure 15 2 is a schematic structural diagram of a device for detecting clarity of a shell-shaped membrane according to another embodiment of the present invention;

[0114] Figure 16 is a block diagram of an exemplary computer system / server suitable for implementing embodiments of the present invention. [Specific implementation method]

[0115] In order to make the purposes, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some but not all of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0116] It should be noted that the terminal involved in the embodiments of the present application can include but is not limited to a mobile phone, a personal digital assistant (PDA), a wireless handheld device, a tablet computer, a personal computer (PC), an MP3 player, an MP4 player, a wearable device (for example, smart glasses, a smart watch, a smart bracelet, etc.), and the like.

[0117] Figure 1 A flowchart of a shell-shaped film pressing clarity detection method of an embodiment of the present application is shown. The method includes the following steps:

[0118] 101. An image to be detected including a bottom surface of an aligner assembly is obtained, the aligner assembly including a light-cured mold and a shell-shaped film formed on the outside of the light-cured mold by film pressing, and the shell-shaped film forms an edge to be detected close to the light-cured mold at the bottom surface;

[0119] Generally, a scanner needs to be used to scan the oral cavity of a patient first to obtain a digital three-dimensional model of the teeth, and then a theoretical model (digital dental model, non-solid) of the dental model corresponding to different treatment stages is generated, and a corresponding solid dental model is printed using a light-cured material. The solid dental model forms a light-cured mold after solidification.

[0120] Then, the hot pressing film after preheating is pressed on the light-cured mold. At this time, the hot pressing film attached to the surface of the light-cured mold becomes a shell-shaped film. The aforementioned aligner assembly is a semi-finished product of the shell-shaped film combined with the light-cured mold. In subsequent processes, through processes such as marking, cutting, and demolding, the aligner assembly finally becomes a finished product.

[0121] In addition, the "shell-shaped film forms an edge to be detected close to the light-cured mold at the bottom surface" means that the hot pressing film forms a main body part matched with the light-cured mold and a hem connecting the main body part in the pressing process. The junction line of the hem and the main body part is the edge to be detected. The edge to be detected is located at the bottom surface of the aligner assembly and imaged in the image to be detected.

[0122] 102, obtaining a gap between a first profile of a bottom outer contour of the light-cured mold and a second profile of a corresponding edge of the to-be-detected edge in the to-be-detected image;

[0123] Here, when the shell-shaped film is pressed on the light-cured mold, an inner ring contour corresponding to the light-cured mold and an outer ring contour corresponding to the shell-shaped film are formed on the bottom surface of the appliance assembly, the outer ring contour and the inner ring contour have a certain gap, the inner ring contour is the bottom outer contour of the light-cured mold, and the outer ring contour is the to-be-detected edge of the shell-shaped film.

[0124] 103, judging the film pressing definition of the shell-shaped film according to the gap.

[0125] Here, when the pressing process of the hot film is successfully completed, the main body part of the shell-shaped film and the light-cured mold should be completely matched, that is, the gap between each corresponding point of the first profile and the second profile at this time should be consistent or within a certain error range, and the subsequent cutting of the appliance can be perfectly matched with the patient's teeth and jaws; when the pressing process of the hot film fails, the gap between each corresponding point of the first profile and the second profile will be too large or too small, and the subsequent cutting of the appliance cannot be perfectly matched with the patient's teeth and jaws.

[0126] That is, the gap between the first profile and the second profile of the embodiment can be used to represent the film pressing definition of the shell-shaped film.

[0127] It should be noted that part or all of the execution subjects of 101-103 can be an application of a terminal device located in a local terminal, i.e., a terminal device of a service provider, or can also be a plug-in or a software development kit (Software Development Kit, SDK) functional unit arranged in the application located in the local terminal, or can also be a processing engine located in a network side server, or can also be a distributed system located in the network side, and the embodiment does not make special limitations.

[0128] It can be understood that the application can be a native program (nativeApp) installed on the terminal, or can also be a web program (webApp) of a browser on the terminal, and the embodiment does not make special limitations.

[0129] In this embodiment, the first profile corresponding to the bottom outer contour of the light-cured mold and the second profile corresponding to the edge to be detected in the image to be detected can be obtained based on the image recognition method. The gap between the first profile and the second profile can be obtained by calculation, and the gap can be used to more intuitively judge the film pressing clarity. The shell-shaped diaphragm pressing mold clarity detection method based on vision in this embodiment realizes efficient identification of unclear pressing molds, thereby obtaining the following advantages: (1) The computer and related vision hardware are used to efficiently complete the pressing mold clarity judgment, thereby reducing the work load of the operators and quality inspectors, improving the production efficiency, and helping to improve the production capacity; (2) The judgment standard based on the gap is more objective and unified, effectively controls the product quality, and helps to form a perfect quality traceability and related feedback mechanism; (3) The detection efficiency is high, the speed is fast, the labor cost is low, and the detection accuracy is high, and it is reliable in complex production environment.

[0130] Next, the flow of the shell-shaped diaphragm pressing mold clarity detection method of this embodiment will be described in detail. Figures 2 to 14

[0131] In one possible implementation of this embodiment, in combination with Figure 2 In step 101, the bottom surface of the appliance assembly 200 can be image collected by adopting the top-down shooting method to obtain the image to be detected including the bottom surface of the appliance assembly 200, which is not particularly limited in this embodiment.

[0132] In a specific implementation, the appliance assembly 200 formed by the light-cured mold 201 and the shell-shaped diaphragm 202 can be placed on a loading platform, a coaxial light source is adopted, the brightness and color of the light source are adjusted, the aperture and focal length of the industrial camera are adjusted, and the top-down shooting method is adopted to collect the image of the appliance assembly 200, so that the clarity of the gray-scale image of the bottom surface of the appliance assembly 200 collected by the industrial camera reaches the best, and the image to be detected is obtained, so as to improve the accuracy of the subsequent profile acquisition process and judgment process.

[0133] In step 101, the "obtaining the image to be detected including the bottom surface of the appliance assembly 200" includes:

[0134] In combination with Figure 2 , the bottom surface image S of the appliance assembly 200 is obtained;

[0135] Here, the bottom surface image S includes the entire bottom surface of the light-cured mold 201 and at least part of the bottom surface of the shell-shaped diaphragm 202 (at least including the entire edge to be detected 2021 of the shell-shaped diaphragm 202).

[0136] In combination with Figure 3 , the bottom surface image S is detected by using the pre-trained posterior tooth area target detection model; ​

[0137] Here, the posterior tooth area target detection model can be obtained based on a deep learning manner, for example, can be implemented through a neural network, but is not limited thereto. The posterior tooth area target detection model is used to detect the posterior tooth area in the bottom surface image S, and a target detection frame S2 is used to select the posterior tooth area in the bottom surface image S.

[0138] According to the robust and reliable target detection model, the embodiment can effectively process special cases and identify difficult cases.

[0139] In combination Figure 4 , in response to the posterior tooth area detected from the bottom surface image S, a to-be-detected image S1 including the posterior tooth area is cropped from the bottom surface image S.

[0140] Here, the to-be-detected image S1 can be cropped from the bottom surface image S with the center position of the target detection frame S2 as the center, and a region image larger than the target detection frame S2 and smaller than the bottom surface image S is cropped according to a preset size expansion ratio of 1.0-1.2 times the size of the target detection frame S2. In this way, the to-be-detected image S1 can include a complete posterior tooth area, and the posterior tooth area can be enlarged to a large extent, so that accurate recognition results can be obtained when subsequent contour recognition is performed based on the to-be-detected image S1, which helps to improve the accuracy of the film pressing clarity detection.

[0141] It should be noted that since the posterior tooth area is relatively prone to film pressing unclearness, the film pressing clarity of the posterior tooth area can be used to represent the film pressing clarity of the entire dental arch area, but is not limited thereto.

[0142] In addition, in the cropping process, two to-be-detected images S1 corresponding to two posterior tooth areas are cropped from the bottom surface image S, and one of the to-be-detected images S1 corresponding to one posterior tooth area is taken as an example for subsequent description.

[0143] In step 102, specifically, an average gap between a first contour L1 corresponding to the bottom outer contour 2011 of the light-cured mold 201 in the to-be-detected image S1 and a second contour L2 corresponding to the to-be-detected edge 2021 is obtained.

[0144] Step 102 includes:

[0145] Obtaining the first contour L1 corresponding to the bottom outer contour 2011 of the light-cured mold 201 in the to-be-detected image S1;

[0146] Specifically, it includes:

[0147] 1021、In combination Figure 5 , a first mask 300 showing the bottom outer contour 2011 of the light-cured mold 201 is obtained according to the to-be-detected image S1;

[0148] Here, the first mask 300 can be obtained by using a flood fill method or a filtering method.

[0149] 1022、Combining Figure 6 to smooth the edges of the first mask 300 to obtain a second mask 301;

[0150] Here, the edges of the first mask 300 include edges corresponding to the bottom outer contour 2011 of the photocuring mold 201 and edges inside the first mask 300. By using a Gaussian smoothing processing method, the second mask 301 with relatively smooth edges can be obtained.

[0151] 1023、Combining Figure 7 and Figure 8 to remove non-connected regions 3011 inside the second mask 301 to obtain a third mask 302;

[0152] Here, the "non-connected regions 3011" refer to regions inside the second mask 301 that are discontinuous with the outer edges of the second mask 301. The existence of the non-connected regions 3011 will affect the subsequent process of obtaining the first contour L1, so the non-connected regions 3011 need to be removed.

[0153] Specifically, in the embodiment, the first edge 3012 of the second mask 301 is obtained by using an edge detection algorithm. Figure 7

[0154] The expression of the first edge 3012 is a binary image, that is, the value of the region corresponding to the first edge 3012 is 255, and the value of the remaining region is 0. The horizontal direction is defined as the width direction, and the vertical direction is defined as the height direction. Each point in the second mask 301 has a height coordinate u in the height direction and a width coordinate v in the width direction. For each height coordinate u, the minimum and maximum width coordinates (vmin, vmax) with a value of 255 are obtained. The points between vmin and vmax are all assigned a value of 255, that is, the non-connected regions 3011 inside the second mask 301 are eliminated to obtain the third mask 302 (see FIG. 3C). Figure 8

[0155] 1024、According to the third mask 302, the first contour L1 corresponding to the bottom outer contour 2011 of the photocuring mold 201 is obtained.

[0156] Here, the first contour L1 can be obtained by using a contour fitting method.

[0157] The step 102 further includes:

[0158] ​​Obtain a second contour L2 corresponding to the edge 2021 to be detected in the image to be detected S1;

[0159] Specifically include:

[0160] 1025, Combination Figure 9 , select multiple target points P distributed at intervals on the first contour L1;

[0161] Here, multiple target points P can be distributed at equal intervals, but can also be distributed at unequal intervals. For example, the interval between adjacent target points P in a relatively flat area of ​​the first contour L1 is larger, and the interval between adjacent target points P in a relatively tortuous area of ​​the first contour L1 is smaller, but this is not limited to it.

[0162] 1026. Obtain the normal vector Z of each target point P away from the light-curing mold 201;

[0163] Here, the target point P from which the normal vector Z is to be obtained is taken as the starting point, and the two points on both sides of the target point P are taken as reference points (the reference points can be other adjacent target points P or randomly selected points). The starting point and the two reference points are connected to obtain two reference vectors, and the reference normal vectors of the two reference vectors are obtained respectively. The two reference normal vectors are normalized, and then the average vector of the two reference normal vectors is obtained (for example, according to the parallelogram law). The average vector is the normal vector Z with the target point P as the starting point.

[0164] 1027. Obtain the grayscale gradient distribution curve of each target point P along the corresponding normal vector Z;

[0165] Specifically, the following steps are included:

[0166] Combine Figure 10 , obtain the grayscale distribution curve of each target point P along the corresponding normal vector Z;

[0167] Combine Figure 11 , smoothing the grayscale distribution curve to obtain a smooth grayscale distribution curve;

[0168] Combine Figure 12 , according to the smooth grayscale distribution curve, the corresponding grayscale gradient distribution curve is obtained.

[0169] Here, the corresponding grayscale gradient distribution curve is obtained by performing a differential operation on the smooth grayscale distribution curve. The grayscale gradient distribution curve is used to represent the degree of grayscale change along the normal vector Z, that is, the smaller the gradient value, the smaller the degree of grayscale change.

[0170] 1028. Obtain the peak point P1 of each grayscale gradient distribution curve;

[0171] Here, the edge 2021 to be detected of the shell-shaped diaphragm 202 formed by compression molding is substantially an arc-shaped edge. The edge 2021 to be detected is not closely fitted with the bottom outer contour 2011 of the photocuring mold 201, but has a certain gap. At this time, as shown in the formed image to be detected S1, in some cases, the bottom outer contour 2011 is displayed as a black circle, the gap between the edge 2021 to be detected and the bottom outer contour 2011 of the photocuring mold 201 is displayed as a white area (due to the reflection of the shell-shaped diaphragm 202), the edge 2021 to be detected is displayed as a black circle again, and on the side away from the photocuring mold 201, due to the reflection of the shell-shaped diaphragm 202, it is displayed as a white area again. The gray values of the black circle and the white area are different, and the gradient values displayed on the gray gradient distribution curve are also different. The peak point P1 of the gradient values other than the target point P is the point with the largest gray value change, and the peak point P1 corresponds to the point of the edge 2021 to be detected.

[0172] In actual operation, the peak point P1 greater than the peak threshold value on each gray gradient distribution curve can be obtained by using a peak searching algorithm. In this way, some small peak points with interference can be filtered out. The peak threshold value is a preset value obtained according to experience.

[0173] 1029、Combining Figure 13 the plurality of peak points P1 to obtain a second contour L2 corresponding to the edge 2021 to be detected.

[0174] After the first contour L1 and the second contour L2 are obtained, step 102 further includes:

[0175] calculating the gap between each corresponding point of the first contour L1 and the second contour L2.

[0176] Here, the gap between each target point P on the first contour L1 and the corresponding peak point P1 located on the normal vector Z of the corresponding target point P can be calculated.

[0177] calculating the average value of the plurality of gaps to obtain an average gap.

[0178] Here, the graph of the calculated average gap is obtained. Figure 14

[0179] Specifically, according to the corresponding relationship between the coordinate system of the industrial camera and the reference coordinate system, the coordinate positions of each point on the first contour L1 and the second contour L2 in the reference coordinate system can be obtained, and then the graph of the average gap can be obtained.

[0180] Step 103 specifically includes:

[0181] 1031、judging the size of the average gap and the gap threshold value;​

[0182] 1032, if not greater than, it is judged that the shell-shaped membrane is in the clear state of the pressed membrane;

[0183] 1033, if greater than, it is judged that the shell-shaped membrane is in the unclear state of the pressed membrane.

[0184] Here, a large number of samples in the clear state of the pressed membrane and the unclear state of the pressed membrane can be obtained in advance, and a gap threshold is obtained according to the samples, which is used for comparison and judgment with the average gap.

[0185] It should be noted that the average gap is used to judge the clear degree of the pressed membrane, which can greatly simplify the calculation process. Of course, in other embodiments, the clear degree of the pressed membrane can also be judged by judging whether the gap at each normal vector Z meets the standard, or by other values.

[0186] Figure 15 The structure schematic diagram of the shell-shaped membrane clear degree detection device provided by another embodiment of the present application.

[0187] The shell-shaped membrane clear degree detection device of the present embodiment includes a first acquisition module 501, a second acquisition module 502 and a determination module 503.

[0188] The first acquisition module 501 is configured to acquire a to-be-detected image including the bottom surface of the appliance assembly, the appliance assembly including a light-cured mold and a shell-shaped membrane formed on the outside of the light-cured mold, the shell-shaped membrane forming a to-be-detected edge close to the light-cured mold at the bottom surface; the second acquisition module 502 is configured to acquire a gap between a first contour corresponding to the bottom contour of the light-cured mold and a second contour corresponding to the to-be-detected edge in the to-be-detected image; and the determination module 503 is configured to determine the clear degree of the pressed membrane of the shell-shaped membrane according to the gap.

[0189] It should be noted that part or all of the clear degree detection device provided by the present embodiment can be an application located in a local terminal, or can also be a plug-in or a software development kit (Software Development Kit, SDK) and the like functional unit arranged in the application located in the local terminal, or can also be a search engine located in a network side server, or can also be a distributed system located in the network side, and the present embodiment does not particularly limit this.

[0190] It can be understood that the application can be a native program (nativeApp) installed on the terminal, or can also be a web program (webApp) of a browser on the terminal, and the present embodiment does not particularly limit this.

[0191] In the embodiment, the first profile of the bottom outer contour of the light-cured mold and the second profile of the to-be-detected edge in the to-be-detected image can be obtained based on the image recognition manner. The gap between the first profile and the second profile can be obtained by calculation, and the film pressing clarity can be more intuitively judged according to the gap. The shell-shaped diaphragm film pressing clarity detection device based on vision in the embodiment realizes efficient identification of unclear film pressing, thereby obtaining the following advantages: (1) the computer and related vision hardware are used to efficiently complete the film pressing clarity judgment, thereby reducing the work load of the operating workers and quality inspection personnel, improving the production efficiency, and assisting in the production capacity improvement; (2) the judgment standard based on the gap is more objective and unified, effectively controls the product quality, and is helpful to form a perfect quality traceability and related feedback mechanism; (3) the detection efficiency is high, the speed is fast, the labor cost is low, and the detection accuracy is high, and the device is reliable in the complex production environment.

[0192] Optionally, in a possible implementation manner of the embodiment, the first obtaining module 501 is specifically configured to:

[0193] The bottom surface of the appliance assembly is imaged in a downward photographing manner to obtain the to-be-detected image including the bottom surface of the appliance assembly.

[0194] Optionally, in a possible implementation manner of the embodiment, the second obtaining module 502 is specifically configured to:

[0195] The average gap between the first profile of the bottom outer contour of the light-cured mold and the second profile of the to-be-detected edge in the to-be-detected image is obtained.

[0196] Optionally, in a possible implementation manner of the embodiment, the first obtaining module 501 is specifically configured to: obtain the bottom surface image of the appliance assembly.

[0197] The device further includes a detection module 504 and a clipping module 505. The detection module 504 is configured to perform target detection on the bottom surface image by using a pre-trained posterior tooth area target detection model. The clipping module 505 is configured to clip the to-be-detected image including the posterior tooth area from the bottom surface image in response to the posterior tooth area detected from the bottom surface image.

[0198] Optionally, in a possible implementation manner of the embodiment, the clipping module 505 is specifically configured to: clip two to-be-detected images respectively corresponding to the two posterior tooth areas from the bottom surface image.

[0199] Optionally, in a possible implementation manner of the embodiment, the second obtaining module 502 is specifically configured to: obtain the first profile of the bottom outer contour of the light-cured mold in the to-be-detected image; and obtain the second profile of the to-be-detected edge in the to-be-detected image.

[0200] The apparatus further includes a calculation module 506 configured to calculate a gap between each corresponding point of the first profile and the second profile, and calculate an average of the plurality of gaps to obtain an average gap.

[0201] Optionally, in a possible implementation of the embodiment, the second acquisition module 502 is specifically configured to:

[0202] acquire a first mask of the bottom outer profile of the light-cured mold according to the image to be detected;

[0203] smooth an edge of the first mask to obtain a second mask;

[0204] remove a non-connected region inside the second mask to obtain a third mask;

[0205] obtain the first profile corresponding to the bottom outer profile of the light-cured mold according to the third mask.

[0206] Optionally, in a possible implementation of the embodiment, the second acquisition module 502 is specifically configured to:

[0207] select a plurality of target points distributed at intervals at the first profile;

[0208] acquire a normal vector of each target point away from the light-cured mold;

[0209] acquire a gray scale gradient distribution curve of each target point along the corresponding normal vector;

[0210] acquire a peak point of each gray scale gradient distribution curve;

[0211] connect the plurality of peak points to obtain a second profile corresponding to the edge to be detected.

[0212] Optionally, in a possible implementation of the embodiment, the second acquisition module 502 is specifically configured to:

[0213] acquire a gray scale distribution curve of each target point along the corresponding normal vector;

[0214] smooth the gray scale distribution curve to obtain a smoothed gray scale distribution curve;

[0215] obtain the corresponding gray scale gradient distribution curve according to the smoothed gray scale distribution curve.

[0216] Optionally, in a possible implementation of the embodiment, the second acquisition module 502 is specifically configured to:

[0217] acquire, by using a peak searching algorithm, a peak point greater than a peak threshold on each gray scale gradient distribution curve.

[0218] Optionally, in a possible implementation manner of the embodiment, the calculation module 506 is specifically configured to:

[0219] calculate the gap between each target point on the first contour and the corresponding peak point.

[0220] Optionally, in a possible implementation manner of the embodiment, the determination module 503 is specifically configured to:

[0221] determine whether the average gap is greater than the gap threshold value;

[0222] if not, it is determined that the shell-shaped diaphragm is in the clear state of the pressed membrane;

[0223] if yes, it is determined that the shell-shaped diaphragm is in the unclear state of the pressed membrane.

[0224] Figure 16 A block diagram of an exemplary computer system / server 600 suitable for implementing embodiments of the present application is shown. Figure 16 The computer system / server 600 is only one example of a computing environment and should not be taken to limit the scope or functionality of embodiments of the present application.

[0225] As shown in Figure 16 The computer system / server 600 is shown in the form of a general-purpose computing device. The components of computer system / server 600 can include, but are not limited to, one or more processors 601, storage 602, which can store one or more programs, and a bus 603 that connects the various system components, including storage 602 and processor 601.

[0226] Bus 603 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration bus, a processor or local bus using any of a variety of bus architectures including Industry Standard Architecture (ISA), Micro Channel Architecture (MCA), Enhanced ISA (EISA), Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.

[0227] Computer system / server 600 typically includes a variety of computer readable media. Such media can be any available media that is accessible by computer system / server 600 and includes both volatile and non-volatile media, removable and non-removable media.

[0228] The storage device 602 can include nonvolatile memory and / or removable memory such as floppy disks, flash memories, and the like. The storage device 602 can also include a storage controller 6023 connecting to the memory 6021 the bus 603. The storage device 602 can be configured to store the operating system, the one or more application programs, the one or more program modules, and / or the program data that are accessible to the computer system / server 600. In one implementation, the storage device 602 is a computer- readable storage medium. In one implementation, the storage device 602 is a computer- readable storage medium. Figure 16 The storage device 602, which is typically (although not exclusively) implemented using a non-removable, nonvolatile memory such as one or more magnetic disk storage devices (generally referred to as "hard disk drives"), can also be used to store the operating system, one or more application programs, the other program modules, and / or program data accessible to the computer system / server 600. In alternative implementations, a non-removable, nonvolatile Figure 16 memory such as one or more magnetic hard disk drives, or a removable, nonvolatile memory such as a magnetic disk or optical disk, can be used in combination with or

[0229] instead of the non-removable, nonvolatile memory devices. As such, the storage device 602 can comprise one or more of the following: a magnetic disk drive for reading from and writing to one or more magnetic disks, an optical disk drive for reading from or writing to one or more optical disks, and / or a solid state drive for reading from and writing to nonvolatile memory solid state devices. The storage device 602 can be connected to the system bus 603 by a storage controller 6023, which can interface with the storage device 602 over an appropriate one or more of the data bus, address bus, and / or control bus.

[0230] The storage device 602 can include a nonvolatile memory and / or a removable memory, such as a floppy disk, a flash memory, and the like. The storage device 602 can also include a storage controller 6023 connecting to the memory 6021 via the bus 603. The storage device 602 can be configured to store the operating system, the one or more application programs, the one or more program modules, and / or the program data accessible to the computer system / server 600. In one implementation, the storage device 602 is a computer-readable storage medium. In one implementation, the storage device 602 is a computer-readable storage medium.

[0231] The processor 601 performs various function applications and data processing by running programs stored in the storage 602, such as implementing Figure 1 The embossing clarity detection method provided by the corresponding embodiment.

[0232] Another embodiment of the present application also provides a computer readable storage medium, which stores a computer program, and the program is executed by a processor to implement Figure 1 The embossing clarity detection method provided by the corresponding embodiment.

[0233] Specifically, any combination of one or more computer readable medium can be used. The computer readable medium can be a computer readable signal medium or a computer readable storage medium. The computer readable storage medium may, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any combination of the above. More specific examples (non-exhaustive list) of the computer readable storage medium include an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, the computer readable storage medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, device or apparatus.

[0234] The computer readable signal medium can include a data signal propagated in a baseband or as a part of a carrier wave, in which a computer readable program code is carried. Such a propagated data signal can take various forms, including but not limited to an electromagnetic signal, an optical signal or any suitable combination of the above. The computer readable signal medium can also be any computer readable medium other than the computer readable storage medium, which can send, propagate or transmit a program for use by or in connection with an instruction execution system, device or apparatus.

[0235] The program code contained in the computer readable medium can be transmitted by any suitable medium, including but not limited to wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0236] Computer program code for carrying out operations of the present application can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0237] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system, device and unit described above can refer to the corresponding process in the foregoing method embodiments, which will not be repeated here.

[0238] In several embodiments provided by the present application, it should be understood that the disclosed system, device and method can be implemented by other ways. For example, the device embodiments described above are only schematic, and for example, the division of the units is only a logical function division, and there can be another division manner in actual implementation, for example, a plurality of units or pages can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or other forms.

[0239] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0240] In addition, each functional unit in each embodiment of the present application can be integrated in one processor, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of hardware plus software functional unit.

[0241] The integrated unit in the form of software function unit can be stored in a computer readable storage medium. The software function unit is stored in a storage medium, and includes a plurality of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute part of steps of the method according to various embodiments of the present application. The storage medium includes a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various storage medium capable of storing program codes.

[0242] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that the technical solutions recorded in the foregoing embodiments can still be modified, or some technical features can be replaced by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for detecting the clarity of a shell-shaped membrane, characterized in that: include: An image of the bottom surface of the orthodontic appliance assembly is obtained by looking up and photographing. The orthodontic appliance assembly includes a light-curing mold and a shell-shaped membrane formed by compression molding on the outside of the light-curing mold. The shell-shaped membrane forms an edge to be detected near the light-curing mold on the bottom surface. Acquire a gap between a first contour corresponding to the bottom outer contour of the light-curing mold and a second contour corresponding to the edge to be detected in the bottom surface image; judging the film pressing clarity of the shell-shaped diaphragm according to the gap; Wherein, obtaining the second contour corresponding to the edge to be detected in the bottom surface image specifically includes: Selecting a plurality of target points distributed at intervals on the first contour; Obtaining a normal vector of each target point away from the light-curing mold; Obtain the grayscale gradient distribution curve of each target point along the corresponding normal vector; Obtain the peak point of each grayscale gradient distribution curve; A plurality of peak points are connected to obtain a second contour corresponding to the edge to be detected.

2. The method according to claim 1, characterized in that The step of "obtaining an image of the bottom surface of the appliance assembly" specifically includes: Using a pre-trained posterior tooth area target detection model, perform target detection on the bottom surface image; In response to the posterior teeth area detected from the bottom surface image, an image to be detected including the posterior teeth area is cropped from the bottom surface image.

3. The method according to claim 2, characterized in that The step of "cropping out the image to be detected including the posterior teeth area from the bottom surface image" specifically includes: Two images to be detected corresponding to two posterior tooth areas are cropped from the bottom surface image.

4. The method according to claim 1, wherein The step of "obtaining a gap between a first contour corresponding to the bottom outer contour of the light-curing mold and a second contour corresponding to the edge to be detected in the bottom surface image" specifically includes: An average gap between a first contour corresponding to the bottom outer contour of the photocurable mold and a second contour corresponding to the edge to be detected is obtained in the bottom surface image.

5. The method according to claim 4, characterized in that The step of "obtaining an average gap between a first contour corresponding to the bottom outer contour of the light-curing mold and a second contour corresponding to the edge to be detected in the bottom surface image" specifically includes: Acquire a first contour corresponding to the bottom outer contour of the light-curing mold in the bottom surface image; Acquire a second contour corresponding to the edge to be detected in the bottom surface image; Calculating a gap between each corresponding point of the first contour and the second contour; The average gap is calculated by averaging the plurality of gaps to obtain an average gap.

6. The method according to claim 5, characterized in that The step of "obtaining a first contour corresponding to the bottom outer contour of the light-curing mold in the bottom surface image" specifically includes: Acquire a first mask showing the bottom outer contour of the light-curing mold according to the bottom surface image; smoothing the edge of the first mask to obtain a second mask; removing the non-connected area inside the second mask to obtain a third mask; A first contour corresponding to the bottom outer contour of the photocurable mold is obtained according to the third mask.

7. The method according to claim 1, characterized in that The step of "obtaining the grayscale gradient distribution curve of each target point along the corresponding normal vector" specifically includes: Get the grayscale distribution curve of each target point along the corresponding normal vector; Smoothing the grayscale distribution curve to obtain a smoothed grayscale distribution curve; A corresponding grayscale gradient distribution curve is obtained according to the smoothed grayscale distribution curve.

8. The method according to claim 1, characterized in that The step of "obtaining the peak point of each grayscale gradient distribution curve" specifically includes: The peak finding algorithm is used to obtain the peak points on each grayscale gradient distribution curve that are greater than the peak threshold.

9. The method according to claim 5, characterized in that The step of "calculating the gap between each corresponding point of the first contour and the second contour" specifically includes: The gap between each target point and the corresponding peak point on the first contour is calculated.

10. The method according to claim 4, characterized in that The step of "determining the film pressing clarity of the shell-shaped diaphragm according to the gap" specifically includes: Determine the size of the average gap and the gap threshold; If it is not greater than, it is judged that the shell-shaped membrane is in a clear membrane pressing state; If it is greater than, it is determined that the shell-shaped membrane is in an unclear membrane pressing state.

11. A device for detecting the clarity of pressed film of a shell-shaped membrane, characterized in that: include: a first acquisition module for acquiring a bottom surface image of the orthodontic appliance assembly by photographing from above, the orthodontic appliance assembly comprising a light-curing mold and a shell-shaped membrane formed by die-casting on the outside of the light-curing mold, the shell-shaped membrane forming an edge to be detected on the bottom surface thereof near the light-curing mold; A second acquisition module is configured to acquire a gap between a first contour corresponding to the bottom outer contour of the light-curing mold and a second contour corresponding to the edge to be detected in the bottom surface image; a determination module, configured to determine the film pressing clarity of the shell-shaped diaphragm according to the gap; The second acquisition module is specifically configured to: Selecting a plurality of target points distributed at intervals on the first contour; Obtaining a normal vector of each target point away from the light-curing mold; Obtain the grayscale gradient distribution curve of each target point along the corresponding normal vector; Obtain the peak point of each grayscale gradient distribution curve; A plurality of peak points are connected to obtain a second contour corresponding to the edge to be detected.

12. The device according to claim 11, characterized in that The device further comprises: a detection module, configured to perform target detection on the bottom surface image using a pre-trained posterior tooth region target detection model; A cropping module is configured to crop an image to be detected including the posterior teeth area from the bottom surface image in response to the posterior teeth area detected from the bottom surface image.

13. The device according to claim 12, characterized in that The cropping module is specifically used to crop two images to be detected corresponding to two posterior tooth areas respectively from the bottom surface image.

14. The device according to claim 11, characterized in that The second acquisition module is specifically used for: An average gap between a first contour corresponding to the bottom outer contour of the photocurable mold and a second contour corresponding to the edge to be detected is obtained in the bottom surface image.

15. The device according to claim 14, characterized in that The second acquisition module is specifically used for: Acquire a first contour corresponding to the bottom outer contour of the light-curing mold in the bottom surface image; and acquire a second contour corresponding to the edge to be detected in the bottom surface image; The device further comprises: The calculation module is configured to calculate a gap between each corresponding point of the first contour and the second contour; and calculate an average value of a plurality of gaps to obtain an average gap.

16. The device according to claim 15, characterized in that The second acquisition module is specifically used for: Acquire a first mask showing the bottom outer contour of the light-curing mold according to the bottom surface image; smoothing the edge of the first mask to obtain a second mask; removing the non-connected area inside the second mask to obtain a third mask; A first contour corresponding to the bottom outer contour of the photocurable mold is obtained according to the third mask.

17. The device according to claim 11, characterized in that The second acquisition module is specifically used for: Get the grayscale distribution curve of each target point along the corresponding normal vector; Smoothing the grayscale distribution curve to obtain a smoothed grayscale distribution curve; A corresponding grayscale gradient distribution curve is obtained according to the smoothed grayscale distribution curve.

18. The device according to claim 11, characterized in that The second acquisition module is specifically used for: The peak finding algorithm is used to obtain the peak points on each grayscale gradient distribution curve that are greater than the peak threshold.

19. The device according to claim 15, characterized in that The calculation module is specifically used for: The gap between each target point and the corresponding peak point on the first contour is calculated.

20. The device according to claim 14, characterized in that The determining module is specifically configured to: Determine the size of the average gap and the gap threshold; If it is not greater than, it is judged that the shell-shaped membrane is in a clear membrane pressing state; If it is greater than, it is determined that the shell-shaped membrane is in an unclear membrane pressing state.

21. A device, characterized in that The device comprises: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 10.

22. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 10 is implemented.

Images