Cradle for generating color clouds

Abstract

The cradle can be used to capture images of objects such as hair. The images can then be used to extract and visualize color information related to the material using a color cloud. A color cloud contains all colors in one or more frames of the image. The cradle includes a video recording device that allows the material to be viewed through a window on the cradle. A smartphone can be used with the cradle to provide lighting as well as to function as a video recording device.

Description

Technology Field

[0001] Cross-reference regarding related applications

[0002] This application claims the benefit of U.S. Application No. 17 / 107,073 filed November 30, 2020; and French Application No. FR2101813 filed February 25, 2021, the entire contents of which are incorporated herein by reference. Background Technology

[0003] Spectrophotometers are used to read the colors of hair swatches, but they provide only a single digital representation of the material in the form of a single RGB, L*a*b*, LCh, or HSV triplet, and typically read only an area smaller than 1 cm x 1 cm. Furthermore, when comparing two materials, the analysis is limited to the Euclidean distance in the color space between the three spaces (e.g., This threshold for ), and detection is not yet determined by humans in hair color. Additionally, a single color (e.g., RGB or L*a*b*) is the average color of a measurement area, and the average color is a mathematical concept rather than a concrete one. Theoretically, for example, one can take the average color of a hair area, and that color may not even exist in that hair area. means of solving the problem

[0004] The present disclosure relates to an apparatus for generating a color cloud, the apparatus comprising: a cradle having a first end, a second end having a window, and at least one wall connecting the first end to the second end; and a video recording device at the first end of the cradle, the video recording device being configured to capture an image of a material visible through the window. In another aspect, the present disclosure also relates to a system for generating a color cloud for an object, the system comprising: a cradle having a first end, a second end having a window, and at least one wall connecting the first end to the second end; an image sensor attached to the first end of the cradle—the image sensor being configured to capture a plurality of digital images of an object visible through the window—; and a processing circuit operably coupled to the image sensor, the processing circuit generating a three-dimensional virtual representation of color information associated with the plurality of digital images of the object; And it is configured to identify one or more important characteristics of the object and to generate one or more virtual instances on a graphic user interface display that represent the identity of the important characteristics of the object based on one or more inputs associated with the three-dimensional virtual representation of the color information of the object.

[0005] In one embodiment, the image recording device is a camera on a mobile device.

[0006] In one embodiment, the device further includes a light source attached to at least one of a first end, a second end, and at least one wall.

[0007] In one embodiment, the light source is a flash light on a mobile device.

[0008] In one embodiment, the device further includes a processing circuit connected to an image recording device and configured to generate a color cloud from an image of a material.

[0009] In one embodiment, the device further includes a holder attached to a first end of a cradle to hold an image recording device.

[0010] In one embodiment, the second end is colored with a plurality of colors adjacent to the window for color separation. Brief explanation of the drawing

[0011] Figure 1 illustrates a user dragging a cradle across their hair to capture an image and generate a color cloud for it. Figure 2 illustrates one method of generating and using a color cloud. FIG. 3 illustrates a first embodiment of a cradle. FIG. 4 illustrates a second embodiment of a cradle, wherein the cradle can be attached to a smartphone. Fig. 5a illustrates the user's hair used to capture an image, wherein the image is captured along the length of the user's hair (starting from their hair roots and ending at their hair tips). FIG. 5b illustrates an example of multiple frames of an image laid out in chronological order, in which the user captured an image of hair starting from the roots and ending at the tips. Figure 6 illustrates an example of a single color cloud that displays all colors from all frames of an image. Figure 7 illustrates an example of a color cloud having color information and frequency information. Figure 8 illustrates an example of four different color clouds generated from samples, which are then overlaid on an L*a*b* color space (projected onto L* and b* dimensions) to visualize their similarities and differences. Figure 9 directly illustrates the shared colors and unique colors between different hairs in the image. Specific details for implementing the invention

[0012] The present disclosure describes a physical device and a proprietary algorithm capable of quantifying optical reflections of any material, such as hair samples on a human head and actual hair, in a manner that is highly repeatable, portable, and operable in any lighting environment. The device, referred to as a cradle, can be used on a material (such as hair) and allows the material to be analyzed by a color cloud algorithm to obtain a total digital representation of the material, defined herein as a color cloud. This color cloud can be compared with other reflective materials or with other color clouds of the same reflective material at different points in time (e.g., colored hair before and after washing). The embodiments disclosed herein extract existing colors from image captures of the materials (and do not manipulate them in any arithmetic manner to produce a net result). This technique may use robust color sets as a basis for detecting subtle color changes.

[0013] FIG. 1 illustrates a use case in one embodiment. A user (101) may take a cradle (102) and drag it over their hair (103). As the cradle (102) is dragged over the user's hair (103), an image of the hair (103) may be obtained. This image may be analyzed using a color cloud algorithm to generate a color cloud.

[0014] FIG. 2 is a flowchart through one embodiment. In S202, an image of a material, such as a user's hair, is acquired using a cradle. For example, to generate a color cloud for the user's hair, the user may run the cradle along the entire length of the hair (i.e., from the root to the tip of the hair). In S204, a color cloud is generated from one or more frames of the image. Essentially, all colors present in one or more frames are extracted and plotted as a color cloud. In S206, the color cloud is compared with other color clouds. This comparison can be used for color matching and / or color differentiation.

[0015] A cradle is a device that enables the capture of an image of a material so that a color cloud of the material can be generated. An example of a cradle is illustrated in FIG. 3 (solid lines indicate the exterior of the cradle, and dotted lines indicate the interior). The cradle has a first end (301), a second end (302), a window (303) on the second end (302), and a wall (304) connecting the first end (301) to the second end (302). In one embodiment, the first end (301) and the second end (302) are located at opposite ends of the cradle. An image sensor, such as an image recording device (305), is attached to the first end (301) inside the cradle and can capture an image of any material (306) (e.g., hair) visible through the window (303). Additionally, the cradle may have a processing circuit (308) connected to an image recording device (305) and may be configured to generate a color cloud from an image of the material (306) and compare the generated color cloud with previous color clouds. The second end (302) of the cradle may be colored with a predetermined set of colors (309) adjacent to the window (303) for color separation when captured by the image recording device (305). The image may capture both the material (306) and the predetermined set of colors (309) adjacent to the window (303) through the window (303); then, the predetermined (i.e., known) colors may be used for reference when determining the color of the material (306). Light (307) may also be attached to the cradle to provide a well-lit view from the image recording device (305) to the window (303). The cradle can be used to maintain a consistent distance between the video recording device (305) and the material (306) when capturing video. The cradle may also have a handle (310).

[0016] The processing circuit (308) may include a color cloud unit and a critical characteristic unit. The color cloud unit may include a circuit coupled to an image sensor and may be configured to generate a three-dimensional virtual representation of color information associated with a plurality of digital images of an object, such as regions representing color occurrence frequency, color variation, or color intensity distribution associated with the object. The critical characteristic unit may include a circuit for identifying one or more critical characteristics of an object and generating one or more virtual instances representing the identity of the object's critical characteristics on a graphical user interface display based on one or more inputs associated with the three-dimensional virtual representation of the object's color information. In one embodiment, the object may be hair, and the three-dimensional virtual representation may be hair color information and / or hair characteristic information associated with a plurality of digital images of hair. Additionally, the three-dimensional virtual representation may include voxels having varying intensity to represent the color frequency of occurrence of a specific characteristic associated with the imaged object. Examples of characteristic information include object identification data, object characteristic data, color frequency of generated data, color change data, color intensity data, absence of color data, and frame-by-frame or pixel-by-pixel color analysis information. Non-limiting examples of color information may include hue, tint, tone, shade, etc. In one embodiment, a tint of a base color is a brighter version of that color, and a shade is a darker version. In one embodiment, tone refers to the lightness (tint) or darkness (shade) of a base color. If the image object is hair, the 3D virtual representation may include hair characteristic information comprising voxels representing gray hair coverage, shine, radiance, and evenness associated with multiple digital images of the hair.Examples of hair characteristics may include hair damage status, concentration of artificial colorants, color distribution, gray coverage, texture, gloss, distribution density, scalp characteristics, etc.

[0017] The body of the cradle of FIG. 3 was essentially a hollow rectangular prism having a window (303) at one end. In one embodiment, when the window (303) is covered, the only light inside the body of the cradle may be from light (307). This can maintain consistent lighting conditions inside the cradle. Also, in other embodiments, the cradle may have different shapes such as a cylinder, a cube, a trapezoidal prism, etc. The cradle may also have a screen, which can be used to visualize a color cloud.

[0018] In one embodiment, the first end of the cradle may be configured to use the camera of a mobile device (e.g., a smartphone) as an image recording device. An example is illustrated in FIG. 4, wherein the first end (401) of the cradle may be an attached smartphone (402). A camera (403) on the smartphone (402) may capture an image of the material (404) through a window (405) on the second end (406). Additionally, a processing circuit already present in the smartphone (402) may be used to generate a color cloud. The color cloud and other related information may be visualized directly on the screen of the smartphone. Additionally, a flash light (407) of the smartphone may be used to provide a well-illuminated view from the smartphone's camera (403) to the window (405). The cradle may also have a holder (408) that allows the smartphone (402) to be properly attached to the cradle when in use and detached from the cradle when not in use.

[0019] The captured image may be of the material for which a color cloud is desired to be generated. The cradle must be held so that the image recording device can capture an image of the material through the opening of the cradle provided by the window. The window may be held directly against the material to block external light from entering the cradle. An example of the material could be hair on the head. In this case, the cradle can start by capturing an image of the roots and then be dragged across the hair to the tips.

[0020] In one embodiment, the video including a plurality of frames may have a length of at least 6 seconds and at least 60 frames per second. If the video captures human hair or a hair sample, the hair may be straight or curly.

[0021] Acquiring an image of the material may involve capturing an image of someone's hair. An example is illustrated in FIGS. 5a and 5b. First, referring to FIGS. 5a, the entire length of the model hair is captured as an image, starting from the root (51a) of the model hair and proceeding downward toward the tip (52a) of the model hair. FIGS. 5b illustrates each frame of the captured image (from FIGS. 5a) laid out in chronological order, where the upper left frame (51b) is of the hair root (51a) and the lower right frame (52b) is of the hair tip (52a). In another embodiment, acquiring an image of the material may involve capturing an image of less than the entire length of someone's hair (e.g., capturing only half of someone's hair). The image may be captured in directions other than downward, such as upward or obliquely.

[0022] A color cloud algorithm can be used to generate a color cloud from one or more frames of an image. The color cloud algorithm can extract color information from one or more frames. The color cloud includes all colors present in one or more of a plurality of frames. In another embodiment, the color cloud includes all colors present in one or more of a plurality of frames and the frequency of all colors present in one or more of a plurality of frames. In another embodiment, the color cloud includes all colors present in one or more of a plurality of frames and the frequency of all colors present in one or more of a plurality of frames, wherein the frequency exceeds a minimum predetermined threshold.

[0023] In one embodiment, a color cloud algorithm can generate a color cloud by extracting all colors from a single frame of an image. For example, in FIG. 5b, individual color clouds can be generated for each frame. The color cloud generated for each frame may include all colors present in that single frame, and, in another embodiment, the frequency of each color present in that single frame.

[0024] In another embodiment, the color cloud algorithm may generate a color cloud by extracting accumulated colors from a group of frames within the image (rather than from a single frame). For example, referring again to FIG. 5b, a color cloud may be generated for each group of 10 frames, wherein the color cloud generated for each group of 10 frames includes all colors present in a specific group of 10 frames, and the frequency of each color present in a group of 10 frames in another embodiment.

[0025] An example of a color cloud is shown in Fig. 6, where the color cloud uses a color space to display all colors across all frames of the image. Since the images are time-based, selecting specific frames can cause the color cloud to be generated at a specific point in time and / or time range.

[0026] When a color cloud algorithm extracts all colors from one or more frames of an image, the color cloud can be displayed in countless forms. For example, colors can be displayed in a color space; the color space can use coordinates such as L*a*b*, RGB, LCh, HSV, etc. to convey color information.

[0027] In another embodiment, the color cloud may contain the frequency (i.e., number) that each color was present in one or more frames of an image. An example is illustrated in FIG. 7, where the brighter a pixel is, the higher the frequency of the color represented by that pixel, and vice versa. The outer color cloud (71) (i.e., full color cloud) captures all colors present in one or more frames, whereas the inner color cloud (72) (i.e., optimized color cloud) captures colors present at a higher frequency. The threshold for determining whether a color is present at a higher frequency can be adjusted according to the application. In one example, only the inner color cloud (72) is used, and low-frequency (i.e., low-information) colors are removed as noise.

[0028] In another embodiment, a color cloud can be used to identify hair characteristics such as gray hair coverage, shine, radiance, evenness, and glow. For example, color and frequency information from the color cloud can be used to extract the amount of gray hair a person possesses by filtering out "low-information" colors and enhancing the detection of colors. As another example, the hair shine level can be calculated by examining the mean, variance, and spatially connected clusters of L* values ​​in the hair color cloud; high variability suggests a wide range of L* values ​​from dark to light, and spatially connected high L* values ​​suggest a band of shine, and these two pieces of information relate to human perception of shine when combined.

[0029] Color clouds can be compared with other color clouds to identify similarities and differences. This can enable color change detection and color matching. An example of comparison with other color clouds is illustrated in Fig. 8. Color clouds are generated for two unwashed samples and for two identical samples after they have been washed. Overlapping portions of the color clouds represent color similarity (i.e., colors present in the two samples), and non-overlapping portions represent color difference (i.e., colors not shared between the samples). This technique quantifies the overlap and non-overlap of groups of color groups (e.g., number of groups, group similarity, average color of the groups) in the color space.

[0030] In addition, similarities and differences between hair colors can be visualized again in an image. An example is illustrated in Fig. 9, where a color cloud was created for a sample before and after washing. Dark areas of the hair represent shared colors, while light areas represent unique colors. Similarities and differences between these color clouds can be identified and visualized directly on the sample. That is, the user can play one of the images used to capture the hair, and similarities / differences can be displayed directly on the hair in the image. This is accomplished by simply matching the color of an image pixel with a color included in one of two different color clouds or in the superposition of two different color clouds. For example, the color of an image pixel that matches any color among the colors within the color cloud superposition or color cloud intersection will be colored dark in the visualized image.

[0031] In another embodiment, an atlas of hair samples may have a directory of color clouds generated for each hair sample. Then, any subsequent captures of hair may have generated color clouds and can be compared with samples within the atlas to determine the closest match (i.e., the most similar color). For good distinction, samples must be more similar to themselves than to other samples.

[0032] The techniques described herein can capture a wide range of reflections (e.g., from hair samples and hair heads) to measure precise and robust heterogeneous materials, such as color, and to measure precise and robust hair color changes. Applications of these techniques may include measuring color changes more precisely and reproducibly than modern instrumentations (e.g., spectrophotometers), measuring human hair color (as a hair colorist can), measuring gray coverage (e.g., measuring the amount of gray at someone's roots to indicate how much hair color product is being used), measuring hair health (e.g., based on gloss levels, where too little gloss indicates dullness and may suggest damaged hair), and dynamic visualizations of hair before and after coloring and / or washing. The techniques described herein may also enable consumer color evaluation at home, display and visualization in stores, and consumer product recommendations at home. For example, consumers can download an app to their phones to capture images and generate a color cloud. The app can additionally recommend hair products based on specific hair characteristics (e.g., recommend specific hair color products based on the user's hair color, gray level, and research conducted within the app). Additionally, the cradle can have portability capabilities (e.g., foldable cardboard cradle, 3D printed cradle, etc.).

Claims

Claim 1 A system for generating a color cloud for an object, comprising: a cradle having a first end, a second end having a window, and at least one wall connecting the first end to the second end; an image sensor attached to the first end of the cradle - the image sensor is configured to capture a plurality of digital images of an object visible through the window -; and a processing circuit operatively coupled to the image sensor, wherein the processing circuit generates a three-dimensional virtual representation of color information associated with the plurality of digital images of the object; and is configured to identify one or more important characteristics of the object and generate one or more virtual instances on a graphical user interface display representing the identity of the important characteristics of the object based on one or more inputs associated with the three-dimensional virtual representation of the color information of the object. Claim 2 A system according to claim 1, wherein the plurality of digital images of the object are included in an image of the user's hair, and the image includes a plurality of frames captured by the image sensor when the cradle moves across the user's hair. Claim 3 In paragraph 2, the system wherein the three-dimensional virtual representation includes all colors present in the plurality of frames of the image. Claim 4 A system according to paragraph 3, wherein the three-dimensional virtual representation includes the frequency at which each color exists in the plurality of frames, and the color existing in the plurality of frames at a frequency below a predetermined threshold is removed as noise from the three-dimensional virtual representation. Claim 5 A system according to claim 1, wherein the image sensor is a camera on a mobile device attached to the first end of the cradle. Claim 6 A system according to claim 1, further comprising a light source attached to at least one of the first end, the second end, and at least one of the at least one wall. Claim 7 In paragraph 6, the system is such that the light source is a flash light on a mobile device attached to the first end of the cradle. Claim 8 A system according to claim 1, further comprising a holder attached to the first end of the cradle to hold the image sensor. Claim 9 A system according to claim 1, wherein the second end is colored with a plurality of colors adjacent to the window for color separation.

Images