Method for identifying the colour of the skin and of the stitching on an automotive interior trim part

Abstract

The method for identifying the color of the skin and the stitching line on the automobile interior trim part belongs to the technical field of image recognition methods, and solves the technical problem of low efficiency of identifying the color of the interior trim part by using the naked eye in the prior art. It comprises the steps of using a camera to shoot the skin of the automobile interior trim part to obtain a picture to be processed; extracting an edge contour in the picture to be processed, the edge contour containing a region image to be identified, the region image to be identified being a region in the edge contour; identifying a stitching line region in the region image to be identified; and determining the color of the skin and the stitching line on the interior trim part according to the stitching line region. The method replaces the traditional manual identification mode with the camera image recognition mode, thereby improving the detection efficiency.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of image recognition method, and particularly relates to a method for recognizing the skin and stitching color of an automobile interior part. BACKGROUND

[0002] The color of the skin and stitching of an automobile interior part needs to be distinguished, and particularly for different configurations of the same vehicle model, only the color of the skin and stitching of two interior parts is different, and other parts are completely the same, and the color difference between the skin and stitching is very small and difficult to be distinguished by the naked eye.

[0003] Therefore, the present application is provided. SUMMARY

[0004] The present application aims to provide a method for recognizing the skin and stitching color of an automobile interior part, and solve the technical problem of low efficiency of recognizing the color of the interior part by the naked eye in the prior art.

[0005] The present application provides a method for recognizing the skin and stitching color of an automobile interior part, and the method comprises the following steps:

[0006] An image of the skin of the automobile interior part is captured by using a camera to obtain a to-be-processed image;

[0007] An edge contour in the to-be-processed image is extracted, the edge contour contains a to-be-recognized region image, and the to-be-recognized region image is a region in the edge contour;

[0008] A stitching region is recognized in the to-be-recognized region image;

[0009] The color of the skin and stitching of the interior part is determined according to the stitching region.

[0010] Compared with the prior art, the technical scheme provided by the present application has the following beneficial effects:

[0011] The method of the present application aims to determine the color of the skin and stitching of the interior part by recognizing the image captured by the camera, and replace the manual recognition mode with the image recognition mode to improve the efficiency of the interior part detection. The recognition of the stitching region can classify the different combinations of the skin color and the stitching color, and the current configuration and the detection of the error in the matching of the skin and stitching color can be recognized. BRIEF DESCRIPTION OF DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required in the embodiments or prior art description. Obviously, the drawings in the following description only represent some of the embodiments of the present application, and for those skilled in the art, other drawings can also be obtained from these drawings without creative labor.

[0013] Figure 1 Flow chart of the method for identifying the color of the skin and the stitching line on the automotive interior part. DETAILED DESCRIPTION

[0014] The above embodiments are only some of the embodiments of the present application, but not all the embodiments. The present application can also be implemented or applied by other different specific embodiments, and each detail in the specification can be modified or changed based on different views and applications without departing from the spirit of the present application. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0015] It should be noted that the various aspects of the embodiments described below are within the scope of the appended claims. It should be apparent that the aspects described herein can be embodied in a wide variety of forms and that any specific structure and / or function described herein is merely illustrative. Based on the present disclosure any aspect described herein can be implemented independently of any other aspect and various examples of implementation are described in the specification. For example, an apparatus can be implemented using any number of the aspects described herein. In addition, an apparatus can be implemented using any number of the aspects described herein in combination. Additionally, an apparatus can be implemented using structure and / or functionality not expressly described herein but nevertheless falling within the scope of the claims.

[0016] It should also be noted that the drawings provided in the following embodiments are only schematic - actual dimensions and shapes of the components can differ from those depicted in the drawings. The drawings are intended to illustrate the basic concept of the present application, and only show the components related to the present application, not the number, shape and size of the components when actually implemented, and the shapes, numbers and proportions of the components can be arbitrarily changed when actually implemented, and the layout of the components can also be more complex.

[0017] In addition, in the following description, specific details are provided to facilitate a thorough understanding of the examples. However, one skilled in the relevant art will understand that aspects can be practiced without these specific details. In order to better understand the present solutions, the present application is described below in connection with the accompanying drawings and detailed description. The terms "first", "second", are used only for the purpose of description, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the technical features indicated. Therefore, the features defined with "first", "second" can explicitly or implicitly include one or more of the features. In the description of the present application, unless otherwise specified, the meaning of "a plurality of" is two or more.

[0018] As shown in the method for identifying the color of the upper skin and the stitching of the automotive interior part, the method comprises: Figure 1

[0019] S101: Use a camera to take a picture of the skin of the automotive interior part to obtain a picture to be processed.

[0020] The existing color distinguishing method is generally visual judgment by human eyes. In this way, people need to remember a very large number of different color combinations of different configurations, and for colors that are difficult to distinguish, it is also easy to make mistakes.

[0021] Secondly, some devices use instruments to measure color, such as colorimeters and spectrometers. In the process of using these instruments, the device needs to be close to the interior part. For the color measurement of very thin areas such as stitching, it is also difficult to obtain accurate results using colorimeters and spectrometers.

[0022] And through the way of acquiring images by the camera, the above situation can be avoided, which is convenient for operation and reduces the detection difficulty.

[0023] S102: Extract the edge contour in the picture to be processed, the edge contour contains the image of the region to be identified, and the image of the region to be identified is the region within the edge contour. Specifically:

[0024] Collect images of the interior part at different positions and / or different angles on the detection table, i.e., the first image;

[0025] The first image is manually labeled with an edge contour to determine the second image;

[0026] The second image is trained using image deep learning software to determine an image segmentation model;

[0027] The edge contour in the picture to be processed is extracted by the image segmentation model.

[0028] ​The edge contour extraction can greatly reduce the data amount processed by the controller, and meanwhile, reduce the cost of hardware, only the image in the edge contour is processed, and the image data outside the edge contour is not considered, so that the approximate area where the stitching line is located can be determined.

[0029] S103: identifying the stitching line area in the to-be-identified region image, specifically:

[0030] The initial position of the stitching line in the to-be-identified region image is determined by the edge detection method. Generally, the stitching line and the stitching line have a spacing of several millimeters on the surface of the interior trim part, and the spacing is the color of the surface. The image area to be identified is determined and then specifically processed.

[0031] The disconnected stitching line area is connected by the morphological method, and the isolated image area is removed to determine the stitching line area. The isolated image area is removed, that is, the features caused by the installation or processing factors are not conducive to the identification of the color of the stitching line. For example, the surface has a fold, and the area of the fold on the image needs to be removed. The feature of the fold on the image is a large gradient. The morphological method is used to process and identify the stitching line area, that is, the identified stitching line area is divided into multiple frames. The gradient of the frame formed by the stitching line is uniform. Therefore, the frame with a large gradient is removed, and the influence of the spacing between the stitching lines is not considered. The removed frame is connected to form a continuous whole line. The color identification of the whole line is the identification of the color of the stitching line.

[0032] The skeleton of the stitching line area is extracted by the skeleton extraction method, and the skeleton is used as a candidate sampling point of the stitching line area.

[0033] That is, the multiple removed frames are extracted by the skeleton extraction method, that is, the whole line is extracted, so as to determine the stitching line area.

[0034] S104: determining the color of the surface and the stitching line on the interior trim part according to the stitching line area.

[0035] The stitching line area is divided into multiple to-be-identified regions, and the size of each to-be-identified region is the same;

[0036] The color and the base color in each to-be-identified region are identified, the color is the color of the stitching line, and the base color is the color of the surface;

[0037] Different combinations of colors and base colors are divided into preset categories, such as "black base white stitching line" as category 0, "black base yellow stitching line" as category 1, and "gray base white stitching line" as category 2.

[0038] The class in each recognition area is identified, and the class with the maximum occurrence probability or the most number of the same class among all classes is determined and output. The computer processing internal factors are considered, which may cause deviation in the identification of the class, and therefore, the class with the most occurrences is used as the final color of the interior trim.

[0039] By obtaining the standard class of the standard interior trim, the standard class is compared with the class of the final determined color.

[0040] Further, considering the influencing factors when the camera is shooting, for example, the different brightness of each area region on the interior trim, or the influence of dark light on the camera, etc. The method of dividing the stitching region into a plurality of to-be-identified regions includes:

[0041] The stitching region is divided into a plurality of initial to-be-identified regions.

[0042] The base color of each initial to-be-identified region is identified, and it is judged whether the base colors of all initial to-be-identified regions are the same or satisfy a preset difference. If yes, the initial to-be-identified region is used as a to-be-identified region. If no, the initial to-be-identified region with different base color or not satisfying the preset range of difference is removed, and the number of the removed initial to-be-identified region is less than that of the initial to-be-identified region with the same base color. The initial to-be-identified region after removal is used as a to-be-identified region.

[0043] The initial to-be-identified region after removal is used as a to-be-identified region, and the accuracy of the overall identification of the interior trim is improved.

[0044] On the other hand, a hardware device for identifying the skin and stitching color on the automotive interior trim is provided, comprising:

[0045] An image to be processed is obtained by using a camera to shoot the skin of the automotive interior trim;

[0046] An edge contour in the image to be processed is extracted, and the edge contour contains a to-be-identified region image, which is a region within the edge contour;

[0047] The stitching region is identified in the to-be-identified region image;

[0048] The color of the skin and the stitching on the interior trim is determined according to the stitching region.

[0049] The color of the skin and the stitching on the interior trim is determined and compared with the standard interior trim.

[0050] Finally, a device for identifying the skin and stitching color on the automotive interior trim is provided, which is suitable for identifying the skin and stitching color on the automotive interior trim on a detection platform, and comprises a camera and a controller electrically connected with the camera, wherein:

[0051] The camera is used to shoot the automotive interior trim on the detection platform;

[0052] The controller acquires the image taken by the camera and is provided with the hardware device as described above.

[0053] Further, the camera is a high-resolution color industrial camera.

[0054] The device of the present application can obtain the classification of different combinations of the skin color and the suture color, can identify the current configuration and perform the detection of the error of the skin suture color matching.

[0055] The product provided by the present application is described in detail above. The principle and implementation mode of the present application are described by applying specific examples in this paper, and the above example description is only used to help understand the core idea of the present application. It should be pointed out that for ordinary skilled persons in the technical field, some improvements and modifications can be made to the present application without departing from the principle of the present application, and these improvements and modifications also fall within the protection scope of the present application.

Claims

1. A method of identifying the color of the skin and the stitching on an automotive interior trim piece, characterized in that, The method comprises: acquiring a to-be-processed picture by taking a skin of an automotive interior part using a camera; extracting an edge contour in the to-be-processed picture, the edge contour containing a to-be-identified region image, the to-be-identified region image being a region within the edge contour; identifying a stitching line region in the to-be-identified region image; determining colors of the skin and the stitching line on the interior part according to the stitching line region; wherein the method of extracting the edge contour in the to-be-processed picture comprises: collecting images of the interior part at different positions and / or different angles on a detection table, i.e., first images; manually labeling the edge contour in the first images to determine second images; training the second images using image deep learning software to determine an image segmentation model; extracting the edge contour in the to-be-processed picture through the image segmentation model.

2. The method of claim 1, wherein, The method of identifying the stitching line region in the to-be-identified region image comprises: determining an initial position of the stitching line in the to-be-identified region image through edge detection; connecting broken stitching line regions through morphological methods to remove isolated image regions to determine the stitching line region; extracting a skeleton of the stitching line region through a skeleton extraction method, the skeleton serving as a candidate sampling point of the stitching line region.

3. The method of claim 1, wherein, The method of determining the colors of the skin and the stitching line on the interior part according to the stitching line region comprises: dividing the stitching line region into a plurality of to-be-identified regions, and the size of each to-be-identified region being the same; identifying a color and a base color in each to-be-identified region, the color being a color of the stitching line, and the base color being a color of the skin; dividing different combinations of the color and the base color into preset categories; identifying a category in each to-be-identified region, determining a category with a maximum appearance probability or a maximum number of the same category among all the categories, and outputting the category.

4. The method of claim 1, wherein, The method of dividing the stitching line region into a plurality of to-be-identified regions comprises: dividing the stitching line region into a plurality of initial to-be-identified regions; identifying a base color of each initial to-be-identified region, and determining whether the base colors of all the initial to-be-identified regions are the same or satisfy a preset difference value, if yes, the initial to-be-identified region is taken as the to-be-identified region, and if no, eliminating the initial to-be-identified regions with different base colors or not satisfying the preset range of the difference value, and the number of the eliminated initial to-be-identified regions is less than that of the initial to-be-identified regions with the same base color, and taking the eliminated initial to-be-identified regions as the to-be-identified regions.

5. A hardware device for identifying the color of the surface layer and stitching of automotive interior parts, characterized in that, The method comprises: acquiring a to-be-processed picture by taking a skin of an automotive interior part using a camera; extracting an edge contour in the to-be-processed picture, the edge contour containing a to-be-identified region image, the to-be-identified region image being a region within the edge contour; identifying a stitching line region in the to-be-identified region image; determining colors of the skin and the stitching line on the interior part according to the stitching line region; wherein the method of extracting the edge contour in the to-be-processed picture comprises: collecting images of the interior part at different positions and / or different angles on a detection table, i.e., first images; manually labeling the edge contour in the first images to determine second images; training the second images using image deep learning software to determine an image segmentation model; extracting the edge contour in the to-be-processed picture through the image segmentation model.

6. A device for identifying the color of the skin and the stitching of an automotive interior trim piece, suitable for identifying the color of the skin and the stitching of an automotive interior trim piece on a detection platform, characterized in that, The utility model relates to a kind of vehicle interior decoration detection platform, including camera and the controller electrically connected with the camera, wherein: The camera is used to take the car interior decoration on detection platform; The controller obtains the image photographed by camera, and is provided with the hardware device as claimed in claim 5.

7. The apparatus of claim 6, wherein, The camera is high-resolution color industrial camera.

Images