Method and device for evaluating glossiness of black paint film

Abstract

The invention discloses a method and a device for evaluating the glossiness of a black paint film. The method comprises the following steps: acquiring a shot image of a to-be-detected target part; obtaining a glossiness value of the to-be-measured target part based on the shot image in combination with a deep learning model; and based on the glossiness value, determining whether the glossiness of the surface of the to-be-detected target part meets the product design requirement or not. According to the invention, the technical problems that the measurement is inaccurate and the measured glossiness does not correspond to the glossiness subjectively evaluated by human vision when a glossmeter is used for measuring the glossiness of the automobile part are solved.

Description

Technical Field

[0001] The invention relates to the technical field of glossiness detection, and in particular to a method and a device for evaluating the glossiness of a black paint film. Background Art

[0002] A gloss meter is usually used to measure the gloss of an object's surface. During the measurement, the gloss measuring device needs to be placed flat and closely on a plane of a certain size of the object to be measured.

[0003] Most automotive parts do not have a flat surface of the required size for gloss meter measurement, and the surface morphology of the base material of castings and forgings is uneven, which makes it difficult to flatten and fit when measuring with a gloss meter, introducing interference from external light. In addition, the specular gloss measured by the instrument represents the size of the reflected light beam in the direction of regular reflection, and sometimes the specular gloss does not correspond to the gloss that relies on subjective evaluation of human vision.

[0004] With regard to the technical problems mentioned above, when using a gloss meter to measure the glossiness of automobile parts, inaccurate measurements may occur, and the measured glossiness does not correspond to the glossiness evaluated subjectively by human vision. No effective solution has been proposed so far. Summary of the invention

[0005] The embodiment of the present invention provides a method and device for evaluating the glossiness of a black paint film, so as to at least solve the technical problem that when using a gloss meter to measure the glossiness of automobile parts, inaccurate measurement may occur and the measured glossiness does not correspond to the glossiness evaluated subjectively by human vision.

[0006] According to one aspect of an embodiment of the present invention, a method for evaluating the glossiness of a black paint film is provided, comprising: obtaining a captured image of a target part to be measured; obtaining a gloss value of the target part to be measured based on the captured image in combination with a deep learning model; and determining whether the glossiness of the surface of the target part to be measured meets product design requirements based on the gloss value.

[0007] Furthermore, before obtaining the gloss value of the target part to be measured based on the captured image and combined with the deep learning model, the deep learning model is constructed and trained, wherein the construction and training of the deep learning model include: obtaining sample images of multiple black paint film samples; performing feature extraction on the sample images to obtain feature information, wherein the feature information includes at least: color information, light source information, curvature information and morphology information; obtaining sample gloss values ​​of multiple black paint film samples; selecting and training a machine model based on the feature information and the sample gloss value; and obtaining a deep learning model based on the trained machine model.

[0008] Furthermore, obtaining sample images of multiple black paint film samples includes: placing the multiple black paint film samples in different shooting environments, wherein the shooting environment at least includes: the light source of the black paint film sample, the placement angle of the black paint film sample, and the bending curvature of the black paint film sample; controlling the camera to shoot the multiple black paint film samples at different shooting angles and different shooting distances to obtain sample images.

[0009] Furthermore, the color information includes the color value of the highlight of the sample image, the color gradient curve of the sample image, the gradient feature of the color gradient curve, the color mean of the sample image and the color variance of the sample image.

[0010] Furthermore, obtaining the sample gloss values ​​of a plurality of black paint film samples includes: measuring the gloss values ​​of the plurality of black paint film samples respectively using a gloss meter in a dark environment.

[0011] Furthermore, according to the feature information and the sample gloss value, a machine model is selected and trained, including: selecting a first machine model, and inputting the feature information and the sample gloss value into the first machine model for calculation and statistics to obtain a color model; selecting a second machine model, and inputting the feature information and the sample gloss value into the second machine model for calculation and statistics to obtain a morphology model; selecting a third machine model, and inputting the feature information and the sample gloss value into the third machine model for calculation and statistics to obtain a light source model; selecting a fourth machine model, and inputting the feature information and the sample gloss value into the fourth machine model for calculation and statistics to obtain a curvature model.

[0012] Furthermore, based on the trained machine model, a deep learning model is obtained, including: constructing a deep learning framework with a multi-input and multi-output structure, integrating the first machine model, the second machine model, the third machine model and the fourth machine model as sub-models into the deep learning framework to obtain an initial learning model; combining feature information, sample gloss value and optimizer to train and optimize the initial learning model to obtain a deep learning model.

[0013] According to another aspect of an embodiment of the present invention, a device for evaluating the glossiness of a black paint film is also provided, including: an acquisition module, the acquisition module is used to acquire a captured image of a target part to be measured; a generation module, the generation module is used to obtain a gloss value of the target part to be measured based on the captured image in combination with a deep learning model; and an evaluation module, the evaluation module is used to determine whether the glossiness of the surface of the target part to be measured meets the product design requirements based on the gloss value.

[0014] According to another aspect of an embodiment of the present invention, a computer storage medium is provided. The computer storage medium includes a stored program, wherein when the program is executed, the device where the computer storage medium is located is controlled to execute the above-mentioned evaluation method.

[0015] According to another aspect of an embodiment of the present invention, a computer program product is provided, including a computer program, and the computer program is executed by a processor to perform the above-mentioned evaluation method.

[0016] In an embodiment of the present invention, a captured image of the target part to be measured is input into a deep learning model to obtain the gloss value of the target part to be measured, and then the surface quality of the target part to be measured is evaluated based on the measured gloss value; wherein, photographing is essentially an extension of the human visual sensory function, that is, the captured image incorporates the subjective evaluation of human vision, and the deep learning model can perform in-depth analysis on the input captured image, without being restricted by the part morphology, so that the measurement result is more accurate. The above-mentioned evaluation method can not only measure parts with uneven surfaces, but also the measurement results incorporate the subjective evaluation of human vision, making the gloss value of the target part to be measured more real and reliable. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0018] Figure 1 This is a hardware structure block diagram of a computer terminal (or mobile device) for implementing a method for evaluating the glossiness of a black paint film according to an embodiment of the present invention;

[0019] Figure 2 It is a flow chart of the method for evaluating the glossiness of a black paint film in the present invention;

[0020] Figure 3 It is a device for evaluating the glossiness of the black paint film in the present invention. DETAILED DESCRIPTION

[0021] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0022] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0023] Example 1

[0024] According to an embodiment of the present invention, an embodiment of a method for evaluating the glossiness of a black paint film is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0025] Figure 1 1 is a hardware structure block diagram of a computer terminal (or mobile device) for implementing a method for evaluating the glossiness of a black paint film according to an embodiment of the present invention. Figure 1 As shown, the computer terminal (or mobile device) may include one or more processors 102 (the processor may include but is not limited to a central processing unit (CPU), a graphics processing unit (GPU), a digital signal processing (DSP) chip, a microprocessor (MCU), a field programmable logic device (FPGA), a neural network processor (NPU), a tensor processing unit (TPU), an artificial intelligence (AI) type processor, etc.) and a memory 104 for storing data. In addition, a transmission device 106 for communication functions, an input and output device 108, and a display 110 may also be included. It can be understood by those skilled in the art that Figure 1 The structure shown is for illustration only and does not limit the structure of the above-mentioned computer terminal (or mobile device). For example, the computer terminal may also include more or fewer components than the above-mentioned structure description, or have a configuration different from the above-mentioned structure description.

[0026] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the black paint film glossiness evaluation method in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, the above-mentioned black paint film glossiness evaluation method is realized. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0027] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0028] The display 110 may be a touch screen type liquid crystal display (LCD). The liquid crystal display may enable a user to interact with a user interface of the mobile terminal. In some embodiments, the mobile terminal has a graphical user interface (GUI), and a user may interact with the GUI by finger contact and / or gestures on a touch-sensitive surface, wherein the human-computer interaction functions here may optionally include the following interactions: creating web pages, drawing, word processing, making electronic documents, games, video conferencing, instant messaging, sending and receiving emails, call interfaces, playing digital videos, playing digital music and / or web browsing, etc. Executable instructions for performing the above human-computer interaction functions are configured / stored in a computer program product or readable storage medium executable by one or more processors.

[0029] Figure 2 : is a flow chart of a method for evaluating the glossiness of a black paint film according to one embodiment of the present invention, such as Figure 2 As shown, the process includes the following steps:

[0030] Step S1: Acquire a photographed image of a target part to be measured.

[0031] Specifically, the target part to be measured is placed under a light source, and a camera is used to photograph the surface to be measured of the target part to obtain a photographed image.

[0032] Step S2: Based on the captured image and combined with the deep learning model, the gloss value of the target part to be measured is obtained.

[0033] Specifically, the captured image is imported into the deep learning model, the deep learning model performs in-depth analysis on the captured image, and then outputs the gloss value of the target part to be tested.

[0034] Step S3: Based on the glossiness value, determine whether the glossiness of the surface of the target part to be measured meets the product design requirements.

[0035] Specifically, the surface of the paint film of the part generally has a gloss requirement (that is, the gloss value of the paint film surface is not lower than a first preset value). When the gloss value of the target part to be measured is higher than the first preset value, the product design requirements are met. When the gloss value of the target part to be measured is lower than the first preset value, the product design requirements are not met.

[0036] In an embodiment of the present application, a captured image of the target part to be measured is input into a deep learning model to obtain the gloss value of the target part to be measured, and then the surface quality of the target part to be measured is evaluated based on the measured gloss value; wherein, shooting is essentially an extension of the human visual sensory function, that is, the captured image incorporates the subjective evaluation of human vision, and the deep learning model can perform in-depth analysis of the input captured image, without being restricted by the part morphology, making the measurement result more accurate. The above-mentioned evaluation method can not only measure parts with uneven surfaces, but also the measurement results incorporate the subjective evaluation of human vision, making the gloss value of the target part to be measured more real and reliable.

[0037] In an exemplary embodiment of the present application, before obtaining the gloss value of the target part to be measured based on the captured image and combined with the deep learning model, the deep learning model is constructed and trained, wherein the construction and training of the deep learning model includes the following steps:

[0038] Step S21: Acquire sample images of a plurality of black paint film samples.

[0039] Step S22: extracting features from the sample image to obtain feature information, wherein the feature information at least includes: color information, light source information, curvature information and shape information.

[0040] Step S23: Obtaining sample gloss values ​​of multiple black paint film samples.

[0041] Step S24: Select and train a machine model based on the feature information and the sample gloss value.

[0042] Step S25: Obtain a deep learning model based on the trained machine model.

[0043] In the above steps S21 to S25, images of multiple black paint film samples are collected to form a sample set, and features are extracted from the images constituting the sample set to reduce the dimension of the data and improve the efficiency of model training; the gloss value of the sample is measured by a gloss meter, and multiple corresponding machine models are selected according to the extracted feature information and the measured gloss value of the sample to establish the relationship between the feature information and the gloss value of the sample, and finally the trained machine models are integrated and processed to obtain a deep learning model.

[0044] Specifically, in step S21, obtaining sample images of a plurality of black paint film samples includes the following steps:

[0045] Step S211: placing a plurality of black paint film samples under different shooting environments, wherein the shooting environment at least includes: a light source for illuminating the black paint film samples, a placement angle of the black paint film samples, and a curvature of the black paint film samples.

[0046] It should be noted that multiple black paint film samples were placed in different shooting environments to ensure the diversity of samples. The light sources include natural light, tungsten lamps, fluorescent lamps, and LED lamps, etc., and the effect of the light source on the glossiness was taken into account. The placement angle refers to the tilt angle of the black paint film sample, and the effect of the tilt angle on the glossiness was taken into account. The setting of different bending radians takes into account the effect of bending on the glossiness.

[0047] Step S212: Control the camera to shoot a plurality of black paint film samples at different shooting angles and different shooting distances to obtain sample images.

[0048] It should be noted that the camera photographed the black paint film sample at different shooting angles and different shooting distances, and the effects of the shooting angle and shooting distance on the glossiness were taken into consideration.

[0049] It should be further explained that the same black paint film sample was photographed using the controlled variable method, that is, changing a parameter in the shooting environment and taking a corresponding image, which helps to analyze the impact of various parameters in the shooting environment on gloss.

[0050] The color information in step S22 includes the color value of the highlight of the sample image, the color gradient curve of the sample image, the gradient feature of the color gradient curve, the color mean of the sample image, and the color variance of the sample image.

[0051] Specifically, the sample image is feature extracted by OpenCV visual software. The color value of the highlight of the image refers to the color value of the brightest part of the sample image; the color gradient curve refers to the color gradient curve of the color value along the divergent direction of the light source with distance as the dependent variable, from which the color gradient range can be analyzed, wherein the color gradient range is related to the scattering of light and the surface roughness of the sample. The gradient feature of the color gradient curve refers to the color change curve within the same color band. Within the color gradient range, the color mean and color variance of each color band are calculated.

[0052] The topography information refers to line scanning of the sample image to obtain the concave-convex information on the sample paint film surface.

[0053] Furthermore, obtaining the sample gloss values ​​of the plurality of black paint film samples in step S23 includes: measuring the gloss values ​​of the plurality of black paint film samples respectively using a gloss meter in a dark environment.

[0054] It should be noted that the measurement was carried out in a dark environment to avoid the introduction of external light due to the uneven surface of the sample, which would affect the measurement results.

[0055] Further, in step S24, according to the feature information and the sample gloss value, a machine model is selected and trained, including the following steps:

[0056] Step S241: Select a first machine model, and input feature information and sample gloss value into the first machine model for calculation and statistics to obtain a color model.

[0057] It should be noted that the first machine model is used to analyze the color information of the sample image and establish the relationship between the color information and the glossiness.

[0058] Step S242: Select a second machine model, and input the feature information and sample gloss value into the second machine model for calculation and statistics to obtain a morphology model.

[0059] It should be noted that the second machine model is used to analyze the morphological information and establish the relationship between the color information and the glossiness.

[0060] Step S243: Select a third machine model, and input the feature information and sample gloss value into the third machine model for calculation and statistics to obtain a light source model.

[0061] It should be noted that the third machine model is used to analyze the illumination light source and establish the relationship between the illumination light source and the glossiness.

[0062] Step S244: Select the fourth machine model, and input the characteristic information and the sample gloss value into the fourth machine model for calculation and statistics to obtain a curvature model.

[0063] It should be noted that the fourth machine model is used to analyze the bending curvature of the sample and establish the relationship between the bending curvature and the glossiness.

[0064] Furthermore, in step S25, a deep learning model is obtained based on the trained machine model, including:

[0065] A deep learning framework with a multi-input and multi-output structure is constructed, and the first machine model, the second machine model, the third machine model and the fourth machine model are integrated into the deep learning framework as sub-models to obtain an initial learning model; the initial learning model is trained and optimized by combining feature information, sample gloss value and optimizer to obtain a deep learning model.

[0066] It should be noted that the optimizer refers to a loss function or a reward function. After the feature information is input into the initial learning model, a preset gloss value is output, and the preset gloss value is compared with the corresponding sample gloss value. The optimizer is adjusted to make the preset gloss value gradually approach the corresponding measured sample gloss value, until the preset gloss value gradually becomes equal to the corresponding measured sample gloss value, and a deep learning model is obtained.

[0067] The deep learning model in the above embodiment is also applied in the field of color rendering simulation.

[0068] In the color rendering simulation software, you can make your own materials with different gloss and roughness, attach these materials to the sample digital model, and evaluate the glossiness of the corresponding materials through the deep learning model under the HDR background environment of the software.

[0069] In a real environment, take a photo of a standard sample; then, in the color rendering simulation software, build a digital model of the sample placed in the same position and direction, so that the position and direction of the camera (window) in the color simulation software is the same as the position and direction of the camera in the real shooting. Use a paint film scanner (Xrite MA-T12 multi-angle spectrophotometer and Pandora software) to scan and collect the Axf material file of the standard sample, and attach the Axf material file to the digital model of the sample in the color rendering software. Use a deep learning model to evaluate the gloss of the sample in the color rendering software, compare it with the gloss of the sample photo in the real environment, manually fine-tune the HDR background environment file parameters, and then use a deep learning model to evaluate the gloss value, continuously reduce the difference, and calibrate the HDR background environment.

[0070] According to another specific embodiment of the present application, a device for evaluating the glossiness of a black paint film is also provided.

[0071] Specifically, Figure 3 As shown, the evaluation device includes: an acquisition module, a generation module and an evaluation module. The acquisition module is used to acquire a photographed image of the target part to be measured. The generation module is used to obtain the gloss value of the target part to be measured based on the photographed image and the deep learning model. The evaluation module is used to determine whether the glossiness of the surface of the target part to be measured meets the product design requirements based on the glossiness value.

[0072] In an embodiment of the present application, a captured image of the target part to be measured is input into a deep learning model to obtain the gloss value of the target part to be measured, and then the surface quality of the target part to be measured is evaluated based on the measured gloss value; wherein, shooting is essentially an extension of the human visual sensory function, that is, the captured image incorporates the subjective evaluation of human vision, and the deep learning model can perform in-depth analysis of the input captured image, without being restricted by the part morphology, making the measurement result more accurate. The above-mentioned evaluation method can not only measure parts with uneven surfaces, but also the measurement results incorporate the subjective evaluation of human vision, making the gloss value of the target part to be measured more real and reliable.

[0073] According to another specific embodiment of the present application, a computer storage medium is also provided. The computer storage medium includes a stored program, wherein when the program is executed, the device where the computer storage medium is located is controlled to execute the above-mentioned evaluation method.

[0074] In this embodiment, the storage medium may be configured to store a computer program for performing the following steps:

[0075] Step S1: Acquire a photographed image of a target part to be measured.

[0076] Step S2: Based on the captured image and combined with the deep learning model, the gloss value of the target part to be measured is obtained.

[0077] Step S3: Based on the glossiness value, determine whether the glossiness of the surface of the target part to be measured meets the product design requirements.

[0078] In an embodiment of the present application, a captured image of the target part to be measured is input into a deep learning model to obtain the gloss value of the target part to be measured, and then the surface quality of the target part to be measured is evaluated based on the measured gloss value; wherein, shooting is essentially an extension of the human visual sensory function, that is, the captured image incorporates the subjective evaluation of human vision, and the deep learning model can perform in-depth analysis of the input captured image, without being restricted by the part morphology, making the measurement result more accurate. The above-mentioned evaluation method can not only measure parts with uneven surfaces, but also the measurement results incorporate the subjective evaluation of human vision, making the gloss value of the target part to be measured more real and reliable.

[0079] According to another specific embodiment of the present application, a computer program product is also provided, including a computer program, and the computer program is executed by a processor to perform the above-mentioned evaluation method.

[0080] In this embodiment, the processor may be configured to perform the following steps through a computer program:

[0081] Step S1: Acquire a photographed image of a target part to be measured.

[0082] Step S2: Based on the captured image and combined with the deep learning model, the gloss value of the target part to be measured is obtained.

[0083] Step S3: Based on the glossiness value, determine whether the glossiness of the surface of the target part to be measured meets the product design requirements.

[0084] In an embodiment of the present application, a captured image of the target part to be measured is input into a deep learning model to obtain the gloss value of the target part to be measured, and then the surface quality of the target part to be measured is evaluated based on the measured gloss value; wherein, shooting is essentially an extension of the human visual sensory function, that is, the captured image incorporates the subjective evaluation of human vision, and the deep learning model can perform in-depth analysis of the input captured image, without being restricted by the part morphology, making the measurement result more accurate. The above-mentioned evaluation method can not only measure parts with uneven surfaces, but also the measurement results incorporate the subjective evaluation of human vision, making the gloss value of the target part to be measured more real and reliable.

[0085] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0086] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0087] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0088] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0089] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0090] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0091] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for evaluating the glossiness of a black paint film, characterized in that: include: Acquire a photographed image of the target part to be measured; Based on the captured image and in combination with a deep learning model, a gloss value of the target part to be measured is obtained; Based on the glossiness value of the target part to be measured, it is determined whether the surface quality of the target part to be measured meets the product design requirements.

2. The evaluation method according to claim 1, characterized in that: Before obtaining the gloss value of the target part to be measured based on the captured image and in combination with the deep learning model, the deep learning model is constructed and trained, wherein the construction and training of the deep learning model includes: Acquire sample images of multiple black paint film samples; Extracting features from the sample image to obtain feature information, wherein the feature information at least includes: color information, light source information, curvature information and shape information; Obtaining sample gloss values ​​of a plurality of the black paint film samples; Selecting and training a machine model according to the feature information and the sample gloss value; Based on the trained machine model, the deep learning model is obtained.

3. The evaluation method according to claim 2, characterized in that: Get sample images of multiple black paint film samples, including: Placing a plurality of the black paint film samples under different shooting environments, wherein the shooting environment at least includes: a light source for illuminating the black paint film sample, a placement angle of the black paint film sample, and a curvature of the black paint film sample; The camera is controlled to shoot the plurality of black paint film samples at different shooting angles and different shooting distances to obtain the sample images.

4. The evaluation method according to claim 2, characterized in that: The color information includes the color value of the highlight of the template image, the color gradient curve of the template image, the gradient feature of the color gradient curve, the color mean of the template image and the color variance of the template image.

5. The evaluation method according to claim 2, characterized in that: Obtaining the sample gloss values ​​of a plurality of the black paint film samples, including: In a dark environment, the gloss values ​​of the plurality of black paint film samples are measured respectively by using a gloss meter.

6. The evaluation method according to claim 2, characterized in that: According to the feature information and the sample gloss value, a machine model is selected and trained, including: Selecting a first machine model, and inputting the characteristic information and the sample gloss value into the first machine model for calculation and statistics to obtain a color model; Selecting a second machine model, and inputting the feature information and the sample gloss value into the second machine model for calculation and statistics to obtain a morphology model; Select a third machine model, and input the characteristic information and the sample gloss value into the third machine model for calculation and statistics to obtain a light source model; A fourth machine model is selected, and the characteristic information and the sample gloss value are input into the fourth machine model for calculation and statistics to obtain a radian model.

7. The evaluation method according to claim 6, characterized in that: Based on the trained machine model, the deep learning model is obtained, including: Constructing a deep learning framework with a multi-input and multi-output structure, integrating the first machine model, the second machine model, the third machine model, and the fourth machine model as sub-models into the deep learning framework to obtain an initial learning model; The initial learning model is trained and optimized in combination with the feature information, the sample gloss value and the optimizer to obtain the deep learning model.

8. A device for evaluating the glossiness of a black paint film, characterized in that: include: An acquisition module, the acquisition module is used to acquire a photographed image of a target part to be measured; A generation module, the generation module is used to obtain the gloss value of the target part to be measured based on the captured image in combination with a deep learning model; An evaluation module is used to determine whether the glossiness of the surface of the target part to be measured meets the product design requirements based on the glossiness value.

9. A computer storage medium, characterized in that The computer storage medium includes a stored program, wherein when the program is executed, the device where the computer storage medium is located is controlled to execute the evaluation method according to any one of claims 1 to 7.

10. A computer program product, comprising a computer program, characterized in that The computer program is used by a processor to execute the evaluation method according to any one of claims 1 to 7.

Images