Lens film color measurement method, system, computer equipment and storage medium

Abstract

This application discloses a lens coating color measurement method, system, computer device, and storage medium, relating to the field of computer technology. The method includes: using a light source and a camera to photograph a coated lens to obtain an image of the coated lens; wherein the power of the light source in a target frequency band is greater than a first threshold, and the target frequency band is a frequency band in which the change in Lab value after reflectivity adjustment is greater than a second threshold; based on the image, determining the red, green, and blue (RGB) values ​​corresponding to the coating color of the coated lens; and determining the Lab value corresponding to the coating color of the coated lens based on the RGB values. This application improves the versatility of lens coating color measurement.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a lens film color measurement method, system, computer equipment, and storage medium. Background Art

[0002] With the advancement of technology, the types and coating systems of coated lenses are increasing, leading to an increasing diversity of lens coating colors. For example, lenses come in a variety of types, including myopia, aging, glitter, and non-glitter. Lenses also vary in thickness and power. There are numerous coating systems available for lenses, with common ones including blue, green, and purple. Different coating systems thicken the lens and filter out glare to varying degrees. Different coating systems, when applied to different types of lenses, create an infinite number of different coating color variations.

[0003] In related technologies, in any lens type and lens film color measurement scenario, a single light source is used to illuminate the coated lens, and expensive professional optical instruments such as colorimeters and customized spectrometers are used to measure the lens film color.

[0004] When using the above method, since the same light source is used to image lenses of various types and film colors, the method cannot be applied to scenes with multiple lens types and multiple film colors. This shows that the method has poor versatility. Summary of the Invention

[0005] The embodiments of the present application provide a lens film color measurement method, system, computer device and storage medium, which can improve the versatility of lens film color measurement.

[0006] In a first aspect, an embodiment of the present application provides a method for measuring lens film color, comprising:

[0007] Using a light source and a camera, photographing the coated lens to obtain an image of the coated lens; wherein the power of the light source in a target frequency band is higher than a first threshold, and the target frequency band is a frequency band in which a change in the Lab value after reflectivity adjustment is greater than a second threshold;

[0008] According to the image, determine the red, green and blue RGB values ​​corresponding to the film color of the coated lens;

[0009] According to the RGB value, determine the Lab value corresponding to the film color of the coated lens.

[0010] In some embodiments, the red R value integral, the green G value integral, and the blue B value integral in the camera sensor spectrum do not interfere with each other.

[0011] In some embodiments, an infrared filter and a UV filter are provided in the camera.

[0012] In some embodiments, determining, based on the image, the red, green, and blue (RGB) values ​​corresponding to the film color of the coated lens includes:

[0013] Determine a target area from the image, where the target area is an overlapping area formed by the reflection of the film color on the front and back surfaces of the coated lens;

[0014] The RGB value of the target area is extracted to obtain the red, green and blue RGB values ​​corresponding to the film color of the coated lens.

[0015] In some embodiments, determining a target region from an image includes:

[0016] The image is input into the first machine learning model for image segmentation and the target area is output.

[0017] In some embodiments, determining the Lab value corresponding to the coating color of the coated lens based on the RGB value includes:

[0018] The RGB value is input into the second machine learning model for processing, and the Lab value corresponding to the film color of the coated lens is output.

[0019] In some embodiments, the second machine learning model includes a first XGBoost model, a second XGBoost model, and a third XGBoost model. The Lab value includes an L value, an a value, and a b value. The RGB value is input into the second machine learning model for processing, and the Lab value corresponding to the film color of the coated lens is output, including:

[0020] The RGB values ​​are input into the first XGBoost model for processing, and the L value corresponding to the film color of the coated lens is output;

[0021] The RGB value is input into the second XGBoost model for processing, and the a value corresponding to the film color of the coated lens is output;

[0022] The RGB value is input into the third XGBoost model for processing, and the b value corresponding to the film color of the coated lens is output.

[0023] In some embodiments, a light source and a camera are used to photograph a coated lens to obtain an image of the coated lens, including:

[0024] The coated lens is photographed using a light source, a camera, and a black box to obtain an image of the coated lens; wherein the light source, the camera, and the coated lens are all located inside the black box.

[0025] In a second aspect, an embodiment of the present application provides a lens film color measurement system, comprising:

[0026] A light source for providing an imaging environment; wherein the power of the light source in a target frequency band is higher than a first threshold, and the target frequency band is a frequency band in which a change in the Lab value after reflectivity adjustment is greater than a second threshold;

[0027] A camera, used for photographing the coated lens to obtain an image of the coated lens;

[0028] The computer device is used to determine the red, green and blue RGB values ​​corresponding to the film color of the coated lens based on the image; and determine the Lab value corresponding to the film color of the coated lens based on the RGB values.

[0029] In a third aspect, an embodiment of the present application provides a computer device, which includes a processor and a memory, wherein the memory stores computer program instructions, and when the processor executes the computer program instructions, the steps of the method of the first aspect are implemented.

[0030] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, which stores computer program instructions. When the computer program instructions are executed by a processor, the steps of the method of the first aspect above are implemented.

[0031] In a fifth aspect, an embodiment of the present application provides a computer program product, which includes computer program instructions. When the computer program instructions are executed by a processor, the steps in the method of the first aspect are implemented.

[0032] It can be seen that the embodiments of the present application have the following beneficial effects:

[0033] When measuring a specific coated lens, a high-power light source suitable for the lens's coating color is selected to image the lens. This allows the light source to fully and accurately capture the coating color, resulting in an image that accurately reproduces the coating color's details. This results in a higher-quality image, and therefore a more accurate Lab value for the coating color. Furthermore, the system can adaptively select different light sources for different coating color measurement scenarios, making it suitable for a variety of lens types and coating color scenarios, thereby improving versatility. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 This is a schematic diagram of the architecture of a lens film color measurement system provided in an embodiment of the present application;

[0035] Figure 2 This is a flow chart of a lens film color measurement method provided in an embodiment of the present application;

[0036] Figure 3 This is a schematic diagram of the structure of a computer device provided in an embodiment of the present application;

[0037] Figure 4It is a structural diagram of a computer-readable storage medium provided in an embodiment of the present application. DETAILED DESCRIPTION

[0038] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and embodiments.

[0039] To facilitate understanding of the technical solutions of the embodiments of the present application, the technical terms involved in the embodiments of the present application will be explained below.

[0040] Red, Green, and Blue (RGB): RGB is an industry color standard. Red (R), Green (G), and Blue (B) represent the colors of the three channels. RGB creates a variety of colors by varying and superimposing these three channels.

[0041] Lab: A color model based on physiological characteristics. Lab consists of three components: lightness (L) and a and b. a and b are two color channels. a ranges from dark green (low lightness) to gray (medium lightness) to bright pink (high lightness); b ranges from bright blue (low lightness) to gray (medium lightness) to yellow (high lightness).

[0042] Region of interest (ROI): The overlapping area of ​​the lens's front and back film color reflections. In some embodiments of the present application, this area is detected using a segmentation algorithm and its RGB values ​​are extracted.

[0043] Exterme Gradient Boosting (Xgboost): Xgboost is an ensemble machine learning algorithm based on decision trees. It uses the gradient boosting framework. Xgboost is a high-performance tree model that selects important features to distinguish samples based on input features during training. The model continuously fits the residuals until convergence.

[0044] Figure 1 Schematic diagram of the structure of a lens film color measurement system provided in an embodiment of the present application. Figure 1As shown, the system includes a light source 10, a camera 11, a coated lens 12, and a computer device 14. The coated lens 12 is arranged below the light source 10 and the camera 11. The light source 10 is used to provide an imaging environment. The camera 11 is used to photograph the coated lens 12, obtain an image of the coated lens 12, and provide the image to the computer device 14. The computer device 14 is used to obtain the Lab value of the film color of the coated lens 12 based on the image. In some embodiments, the camera 11 and the computer device 14 are connected via a wired network or a wireless network, and the camera 11 transmits the captured image to the computer device 14 via the network. In some embodiments, the system also includes a black box 13, and the light source 10, the camera 11, and the coated lens 12 are all arranged inside the black box 13. Figure 1 Please refer to the method flow of how the system measures the lens film color. Figure 2 The method embodiment shown.

[0045] The following is an example of the method flow of the embodiment of the present application.

[0046] Figure 2 This is a flow chart of a lens film color measurement method provided in an embodiment of the present application. Figure 2 The system architecture on which the method is based is as follows Figure 1 For example, Figure 1 The computer device 14, the light source 10 and the camera 11 cooperate to perform step S201 to obtain an image of the coated lens 12; Figure 1 The computer device 14 executes steps S202 to S203 to obtain the Lab value of the film color of the coated lens 12 . Figure 2 The method shown includes the following steps S201 to S203.

[0047] Step S201: The computer device uses a light source and a camera to photograph the coated lens to obtain an image of the coated lens.

[0048] There are many types of coated lenses. From the perspective of lens type, the coated lenses may have lens types such as presbyopia, myopia, or glare. From the perspective of the coating system, the coated lenses may have coatings such as green, blue, or purple. Both the lens type and the coating system affect the lens coating color. For example, lenses of different lens types may have different coating colors, and lenses of different coating systems may have different coating colors.

[0049] The power of the aforementioned light source in the target frequency band is higher than the first threshold. By selecting a light source with sufficient power within the target frequency band as the imaging light source for the coated lens, imaging can be performed using a high-energy light source suitable for the film color characteristics, which helps to accurately capture the lens film color information and facilitates the subsequent accurate restoration of the film color Lab value.

[0050] The target frequency band is the frequency band where the change in the Lab value after reflectivity adjustment exceeds the second threshold. Because slight changes in reflectivity at the target frequency band result in significant changes in the Lab value, and the Lab value is a quantitative measure of the lens coating color, the target frequency band can be understood as the frequency band that contributes to the coating color of the coated lens, or the frequency band that is important to the coating color. The target frequency band can more fully reflect the coating color details.

[0051] In some embodiments, the target frequency band is determined based on the reflectivity curve of the film color on the lens. The reflectivity curve, for example, describes the relationship between frequency bands and reflectivity. For example, a comparative experiment may be conducted, including: adjusting the reflectivity of the film color at the current frequency band by a set multiple, such as increasing the reflectivity by any multiple between 1 and 5 times, or reducing the reflectivity by any multiple between 1 and 5 times; then, calculating the Lab value of the film color after the reflectivity adjustment (the Lab value of the film color can be calculated using the reflectivity and a fixed formula), and calculating the change in L value after the reflectivity adjustment compared to the L value before the reflectivity adjustment, the change in a value after the reflectivity adjustment compared to the a value before the reflectivity adjustment, and the change in b value after the reflectivity adjustment compared to the b value before the reflectivity adjustment. If the change in L value, a value, or b value exceeds a set change threshold, such as a change greater than 0.5 (i.e., any of the L value, a value, or b value increases or decreases by more than 0.5), the frequency band is considered important and is then designated as the target frequency band.

[0052] The above-mentioned camera can be a true color camera. The R value integral, G value integral, and B value integral in the sensor spectrum of the camera do not interfere with each other. The R value integral is, for example, the integral of the spectral response curve corresponding to the red frequency band in the sensor spectrum. The G value integral is, for example, the integral of the spectral response curve corresponding to the green frequency band in the sensor spectrum. The B value integral is, for example, the integral of the spectral response curve corresponding to the blue frequency band in the sensor spectrum. The R value integral, G value integral, and B value integral do not interfere with each other, which can mean that the area of ​​the overlapping region between the spectral response curves corresponding to the red frequency band, the spectral response curve corresponding to the blue frequency band, and the spectral response curve corresponding to the green frequency band is less than the area threshold, that is, the intersection between the three spectral response curves is as small as possible. The horizontal axis of the spectral response curve is the frequency band, and the vertical axis is the spectral response. By combining the sensor spectrum of the camera and selecting a camera whose RGB color value integrals do not interfere with each other for imaging, it helps to avoid the three RGB color values ​​from being interfered with by irrelevant color combinations, thereby helping to improve the accuracy of the subsequent extraction of RGB values.

[0053] In some embodiments, the camera is provided with an infrared filter and an ultraviolet filter. The use of the infrared filter and the ultraviolet filter enables the camera to block the infrared and ultraviolet frequency bands, which are non-color-rendering frequency bands, thereby eliminating interference of the infrared and ultraviolet frequency bands on the RGB value integration.

[0054] In this embodiment, by selecting a light source and a camera with the above characteristics, it is helpful to more accurately restore the color information of the film color, so when the Lab value is subsequently calculated using RGB value modeling, it is helpful to improve the accuracy of the Lab value.

[0055] In some embodiments, the process of photographing a coated lens, that is, the lens imaging process, includes: placing the lens below a light source and a camera, with the distance between the center of the lens and the center of the camera being less than a first distance threshold, and the distance between the center of the lens and the center of the light source being less than a second distance threshold. In traditional solutions, professional optical instruments are usually used to measure the film color of coated lenses, and professional and sophisticated instrument calibration processes need to be designed. When measuring the lens, the instrument needs to be strictly aligned with the center and left to stand for 2 to 3 seconds, resulting in greater measurement difficulty and high cost. Compared to traditional solutions, in this embodiment, there is no need to use professional optical instruments or sophisticated instrument calibration processes. Instead, a specific light source and camera are used to ensure that the center of the lens does not deviate too far from the center of the camera and light source. Therefore, there is a higher degree of freedom, which reduces the cost and difficulty of film color measurement in scenarios compatible with different lens types and different film systems, and reduces the cost and operational threshold of film color measurement for coated lenses.

[0056] In some embodiments, a light source, a camera, and a black box are used to capture images of the coated lens, where the light source, camera, and coated lens are all located within the black box. The black box can block external light sources, resulting in a cleaner imaging environment and reduced noise.

[0057] Step S202: The computer device determines the RGB value corresponding to the film color of the coated lens based on the image.

[0058] In some embodiments, after the camera captures an image of the coated lens, the image of the coated lens is sent to a processor of a computer device. The processor receives the image from the camera and executes step S202 based on the image.

[0059] In some embodiments, step S202 includes:

[0060] Determine a target area from the image, where the target area is an overlapping area formed by the reflection of the film color on the front and back surfaces of the coated lens;

[0061] The RGB value of the target area is extracted to obtain the red, green and blue RGB values ​​corresponding to the film color of the coated lens.

[0062] The target area, also known as the ROI, is the overlapping region formed by the reflections of the film color from the front and back surfaces of a coated lens. Specifically, since both the front and back surfaces of the lens are coated, the film color appears on both sides. Under illumination from a light source, the reflections from the front and back surfaces of the lens will overlap, and the film color information in this overlapping region is relatively accurate. In this embodiment, by identifying this overlapping region from the image and determining the Lab value of the film color based on the RGB values ​​of this overlapping region, the accuracy of the Lab value of the film color is improved.

[0063] In some embodiments, the target region is segmented from the image by machine learning. Specifically, the image is input into a first machine learning model for image segmentation, and the target region is output.

[0064] The first machine learning model is, for example, a deep learning model, such as a neural network model. In some embodiments, the first machine learning model is trained based on a sample image set. The sample image set includes multiple images of coated lenses. Each image in the sample image set is annotated with an overlapping region formed by reflections of the coating color on the front and back surfaces.

[0065] Step S203: The computer device determines the Lab value corresponding to the film color of the coated lens according to the RGB value.

[0066] In some embodiments, RGB values ​​are mapped to Lab values ​​using machine learning. Specifically, the RGB values ​​are input into a second machine learning model for processing, and the Lab value corresponding to the coating color of the coated lens is output.

[0067] In some embodiments, RGB values ​​are mapped to Lab values ​​using three XgBoost models, which are used to predict L values, a values, and b values, respectively. Specifically, the second machine learning model includes a first XGBoost model, a second XGBoost model, and a third XGBoost model. The first XGBoost model is used to map RGB values ​​to L values ​​in Lab values, the second XGBoost model is used to map RGB values ​​to a values ​​in Lab values, and the third XGBoost model is used to map RGB values ​​to b values ​​in Lab values.

[0068] Accordingly, step S203 includes:

[0069] The RGB values ​​are input into the first XGBoost model for processing, and the L value corresponding to the film color of the coated lens is output;

[0070] The RGB value is input into the second XGBoost model for processing, and the a value corresponding to the film color of the coated lens is output;

[0071] The RGB value is input into the third XGBoost model for processing, and the b value corresponding to the film color of the coated lens is output.

[0072] For the three XGBoost models described above, mapping RGB values ​​to Lab values ​​is equivalent to a regression task. During the training phase, the model internally establishes a mapping relationship between RGB and Lab values. Therefore, during the measurement phase, the model can predict L, a, or b values ​​based on RGB values. The XGBoost model achieves faster convergence and higher accuracy during training. Compared to neural networks, the XGBoost model requires fewer samples, resulting in better results.

[0073] Alternatively, instead of using the XGBoost model as the second machine learning model, a random forest, a neural network or other types of machine learning models can be used as the second machine learning model. This embodiment does not limit the type of the second machine learning model.

[0074] In the above steps 202 to S203, the lens film color is measured by using machine learning, which realizes automatic processing after the lens is placed for imaging. Basically, no human intervention and interaction are required, and the Lab value of the film color information of the coated lens can be estimated, thereby saving time and improving efficiency.

[0075] In the method provided in this embodiment, when measuring a specific coated lens, a high-power light source suitable for the lens's coating color is selected to image the lens. This allows the light source to fully and accurately capture the lens' coating color, and the resulting image accurately restores the coating color details. This results in higher-quality images, and therefore more accurate Lab values ​​for the coating color obtained from the image. Furthermore, the method can adaptively select different light sources for measurement in different coating color scenarios, making it applicable to a variety of lens types and coating color scenarios, thereby improving versatility.

[0076] Figure 3 The computer device 300 is a schematic diagram of a structure of a computer device 300 provided in an embodiment of the present application. The computer device 300 includes a processor 301 and a memory 302. The memory 302 stores computer program instructions. When the processor 301 executes the computer program instructions, the above-mentioned Figure 2 The steps of the method are shown in the embodiment.

[0077] Figure 4 The computer readable storage medium 400 is a schematic diagram of the structure of the embodiment of the present application. The computer readable storage medium stores computer program instructions 401. When the computer program instructions 401 are executed by the processor, the above Figure 2 The steps of the method are shown in the embodiment.

[0078] The present application also provides a computer program product, which includes computer program instructions. When the computer program instructions are executed by a processor, the above Figure 2 The steps of the method are shown in the embodiment.

[0079] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Reference can be made to the common and similar parts between the various embodiments. For the systems or devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple, and the relevant parts can be referred to the method description.

[0080] It should also be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.

[0081] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0082] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present application. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not limited to the embodiments shown herein, but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for measuring lens film color, characterized in that: include: Using a light source and a camera, photographing the coated lens to obtain an image of the coated lens; wherein the power of the light source in a target frequency band is higher than a first threshold, and the target frequency band is a frequency band in which a change in the Lab value after reflectivity adjustment is greater than a second threshold; Determining, based on the image, the red, green, and blue (RGB) values ​​corresponding to the film color of the coated lens; Determining the Lab value corresponding to the film color of the coated lens according to the RGB value; The process of determining the target frequency band includes: At the current frequency band, adjust the reflectivity of the film color by a set multiple; Calculate the change between the L value after the reflectivity adjustment and the L value before the reflectivity adjustment, the change between the a value after the reflectivity adjustment and the a value before the reflectivity adjustment, and the change between the b value after the reflectivity adjustment and the b value before the reflectivity adjustment; If the change in the L value, the change in the a value, or the change in the b value is greater than the change threshold, the current frequency band is used as the target frequency band.

2. The method according to claim 1, characterized in that The red R value integral, the green G value integral and the blue B value integral in the sensor spectrum of the camera do not interfere with each other.

3. The method according to claim 2, characterized in that The camera is provided with an infrared filter and an ultraviolet filter.

4. The method according to claim 1, wherein Determining, based on the image, the red, green, and blue (RGB) values ​​corresponding to the film color of the coated lens includes: Determining a target area from the image, wherein the target area is an overlapping area formed by reflections of the film colors on the front and back surfaces of the coated lens; RGB values ​​of the target area are extracted to obtain red, green, and blue RGB values ​​corresponding to the film color of the coated lens.

5. The method according to claim 4, characterized in that Determining the target area from the image includes: The image is input into a first machine learning model for image segmentation, and a target area is output.

6. The method according to claim 1, wherein Determining the Lab value corresponding to the film color of the coated lens according to the RGB value includes: The RGB value is input into a second machine learning model for processing, and the Lab value corresponding to the film color of the coated lens is output.

7. The method according to claim 6, characterized in that The second machine learning model includes a first XGBoost model, a second XGBoost model, and a third XGBoost model, the Lab value includes an L value, an a value, and a b value, and the RGB value is input into the second machine learning model for processing to output the Lab value corresponding to the film color of the coated lens, including: Inputting the RGB value into the first XGBoost model for processing, and outputting the L value corresponding to the film color of the coated lens; Inputting the RGB value into the second XGBoost model for processing, and outputting the a value corresponding to the film color of the coated lens; The RGB value is input into the third XGBoost model for processing, and the b value corresponding to the film color of the coated lens is output.

8. The method according to any one of claims 1 to 7, characterized in that The method of photographing the coated lens using a light source and a camera to obtain an image of the coated lens includes: The coated lens is photographed using a light source, a camera, and a black box to obtain an image of the coated lens; wherein the light source, the camera, and the coated lens are all arranged inside the black box.

9. A lens film color measurement system, characterized in that: include: A light source for providing an imaging environment; wherein the power of the light source in a target frequency band is higher than a first threshold, and the target frequency band is a frequency band in which the change in the Lab value after reflectivity adjustment is greater than a second threshold; A camera, used to photograph the coated lens to obtain an image of the coated lens; A computer device, configured to determine, based on the image, the red, green, and blue (RGB) values ​​corresponding to the film color of the coated lens; and determine, based on the RGB values, the Lab value corresponding to the film color of the coated lens; The process of determining the target frequency band includes: At the current frequency band, adjust the reflectivity of the film color by a set multiple; Calculate the change between the L value after the reflectivity adjustment and the L value before the reflectivity adjustment, the change between the a value after the reflectivity adjustment and the a value before the reflectivity adjustment, and the change between the b value after the reflectivity adjustment and the b value before the reflectivity adjustment; If the change in the L value, the change in the a value, or the change in the b value is greater than the change threshold, the current frequency band is used as the target frequency band.

10. A computer device, characterized in that: The computer device includes a processor and a memory, wherein computer program instructions are stored in the memory, and when the processor executes the computer program instructions, the steps of the method according to any one of claims 1 to 8 are implemented.

11. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer program instructions, which, when executed by a processor, implement the steps of the method according to any one of claims 1 to 8.

Images