Color master batch color detection method and device, computer equipment and storage medium

Abstract

The invention relates to the technical field of visual detection, in particular to a color master batch color detection method and device, computer equipment and a storage medium, and the color master batch color detection method comprises the following steps: obtaining to-be-detected environment data, and obtaining environment illumination intensity and environment illumination direction from the to-be-detected environment data; obtaining the color of a to-be-detected color master batch, obtaining corresponding detection environment requirement data according to the color of the to-be-detected color master batch, and comparing the detection environment requirement data with the environment illumination intensity and the environment illumination direction to obtain an illumination comparison result; adjusting the to-be-detected environment data according to an illumination comparison result, obtaining a color master batch detection image, and performing spectrum detection on the color master batch detection image to obtain a color difference detection result; and analyzing the chromatic aberration detection result, obtaining an abnormal chromatic aberration position according to a corresponding analysis result, and marking according to the abnormal chromatic aberration position. The method has the effect of improving the color detection precision of the color master batch.

Description

Technical Field

[0001] The present application relates to the technical field of visual detection, and in particular to a method, device, computer equipment and storage medium for detecting color of masterbatch. Background Art

[0002] At present, in the precision links of modern manufacturing, intelligent visual inspection technology has become the cornerstone of product quality control, especially in the manufacturing process of products such as masterbatch that require high color consistency. Although traditional visual inspection technology has shown certain effectiveness and reliability in fixed and standardized production environments, it has obvious limitations when placed in variable actual production scenarios, especially when lighting conditions are unstable, color temperature fluctuates, and material surface reflective properties vary. It is difficult to maintain consistent inspection accuracy, thus introducing uncertainty and potential quality risks.

[0003] At present, the industry relies on image processing methods with preset static models, such as grayscale division with fixed thresholds and rigid RGB color space conversion rules, in an attempt to achieve the goal of automatic color monitoring of masterbatch. This method may be feasible in an idealized test environment, but it has many shortcomings when faced with complex actual production conditions.

[0004] The above-mentioned prior art solutions have the following defects: Under the influence of sudden changes in light intensity at the production site, dynamic adjustments in color temperature, and the diverse reflective characteristics of the masterbatch surface, traditional visual inspection systems based on fixed models frequently experience color recognition errors, especially the ability to identify subtle color differences and the accuracy of color uniformity judgment. Summary of the invention

[0005] In order to improve the accuracy of color detection of masterbatches, the present application provides a masterbatch color detection method, device, computer equipment and storage medium.

[0006] The above-mentioned invention objective of the present application is achieved through the following technical solutions: A method for detecting color of a masterbatch, comprising: Acquire the environmental data to be detected, and acquire the ambient light intensity and the ambient light direction from the environmental data to be detected; Acquire the color of the masterbatch to be detected, acquire corresponding detection environment requirement data according to the color of the masterbatch to be detected, and compare the detection environment requirement data with the ambient light intensity and ambient light direction to obtain a light comparison result; The environmental data to be detected is adjusted according to the illumination comparison result, a masterbatch detection image is obtained, and a spectrum detection is performed on the masterbatch detection image to obtain a color difference detection result; The color difference detection result is analyzed, the abnormal color difference position is obtained according to the corresponding analysis result, and the abnormal color difference position is marked.

[0007] By adopting the above technical solution, the detection consistency under different lighting conditions is ensured by obtaining the environmental data to be detected and extracting the ambient light intensity and ambient light direction from it. Then, based on the color information of the masterbatch to be detected, the corresponding detection environment requirement data is obtained, and it is compared with the actual ambient light conditions to obtain the light comparison result, so that the environmental data to be detected can be automatically adjusted, so that high-quality masterbatch detection images can be obtained under various lighting conditions; by performing spectral detection on the masterbatch detection image, the band spectral data of each pixel point can be accurately identified, and the color characteristics of the masterbatch can be further extracted. This process not only improves the speed of color difference detection, but also greatly improves the recognition accuracy and reliability. Then, by analyzing the image frequency domain data in the color difference detection result, the image frequency distribution is obtained, and the abnormal color difference position on the masterbatch surface is accurately identified and marked, which is convenient for the operator to perform subsequent processing.

[0008] In a preferred example, the present application may be further configured as follows: before obtaining the color of the masterbatch to be detected and obtaining the corresponding detection environment requirement data according to the color of the masterbatch to be detected, the masterbatch color detection method further includes: Acquire historical masterbatch production data, and acquire masterbatch color data and corresponding abnormal color detection data from the historical masterbatch production data; Performing illumination tests under different illumination conditions on each of the masterbatch color data, and obtaining abnormal color images corresponding to the abnormal color detection data of each of the masterbatch color data under different illumination conditions; Abnormal color difference data in each abnormal color image is obtained, and the lighting condition under which the abnormal color difference data is the highest is obtained, and the data is associated with the masterbatch color data to obtain a corresponding color association model.

[0009] By adopting the above technical solution, before obtaining the color of the masterbatch to be detected, the historical masterbatch production data is first obtained, and the masterbatch color data and abnormal color detection data are extracted therefrom. By performing illumination tests on each masterbatch color data in the historical data under different illumination conditions, the abnormal color images corresponding to the masterbatch under various illumination conditions are obtained, thereby extracting the abnormal color difference data in each abnormal color image, and then determining the abnormal color difference performance under various illumination conditions. After identifying the illumination conditions under which each masterbatch color is most likely to have abnormal color difference, this information is summarized and associated to form a corresponding color association model, which can provide a reference for the subsequent actual production of the masterbatch to be detected. It provides accurate lighting condition recommendations in the detection environment, avoids detection errors caused by inappropriate lighting conditions, improves the accuracy and consistency of detection results, and ensures that reliable color detection results can be obtained in complex and changeable actual production environments. This not only effectively reduces detection errors caused by lighting factors, but also makes the color detection results of masterbatches more accurate and reliable through refined control and optimization of lighting conditions, greatly improving the level of color management in the production process. This not only ensures the high consistency and reliability of color detection results, but also provides a solid data foundation for subsequent intelligent adjustments, significantly improving production efficiency and product quality.

[0010] In a preferred example, the present application can be further configured as follows: the step of obtaining the color of the masterbatch to be detected and obtaining the corresponding detection environment requirement data according to the color of the masterbatch to be detected specifically includes: Inputting the color of the masterbatch to be detected into the color association model to obtain detection light condition data; The detection environment requirement data is generated according to the detection lighting condition data.

[0011] By adopting the above technical solution, by inputting the color of the masterbatch to be detected into the pre-established color association model, the detection illumination condition data most suitable for the masterbatch can be obtained, and then the accurate detection environment requirement data can be generated. This technical means ensures that the color detection of the masterbatch can reach the optimal state under various lighting conditions, that is, when receiving the new color of the masterbatch to be detected, the detection illumination condition most suitable for this type of masterbatch can be quickly determined, ensuring that the color deviation problem caused by inappropriate lighting is avoided when obtaining the masterbatch detection image, thereby not only significantly improving the accuracy and reliability of the masterbatch color detection, but also effectively overcoming the problem of reduced detection accuracy caused by changes in lighting conditions, and by adjusting to the optimal detection lighting conditions in advance, it can always maintain stable detection performance in a variety of complex production environments. In addition, this method also helps to reduce the frequency of manual intervention and improve production efficiency. In actual applications, when the masterbatch varieties on the production line are frequently switched, there is no need to rely on manual readjustment of the lighting condition settings every time. The optimal detection parameters can be automatically matched to ensure that each detection can be carried out under the most suitable lighting conditions. This improvement not only simplifies the operating process, but also improves the overall work efficiency of the production line, ensuring that each batch of masterbatch produced can meet high standards in color consistency and meet the strict requirements of high-end manufacturing.

[0012] In a preferred example, the present application may be further configured as follows: performing spectral detection on the masterbatch detection image to obtain a color difference detection result specifically includes: Acquire the band spectrum data corresponding to each pixel from the masterbatch detection image, and extract the masterbatch color characteristics according to the band spectrum data; The color characteristics of the masterbatch of each pixel are analyzed by a deep neural network to obtain the color difference detection result.

[0013] By adopting the above technical solution, by performing spectral detection on the masterbatch detection image, the band spectral data corresponding to each pixel can be obtained, and the masterbatch color characteristics can be extracted based on these band spectral data. Furthermore, the masterbatch color characteristics of each pixel are analyzed through a deep neural network to obtain accurate color difference detection results. The deep neural network has the ability to accurately identify and distinguish the colors of masterbatch under various lighting conditions through learning from a large number of masterbatch samples in real scenes, thereby achieving micron-level color difference diagnosis, which not only improves the detection speed and accuracy, but also effectively reduces the probability of misjudgment and missed detection, ensuring the consistency and uniformity of the masterbatch color. Especially in complex production environments, through real-time feedback and intelligent tuning, the system can automatically adjust production parameters according to the detection results, thereby significantly improving production efficiency and product quality.

[0014] In a preferred example, the present application may be further configured as follows: analyzing the color difference detection result and obtaining the abnormal color difference position according to the corresponding analysis result specifically includes: Acquire image frequency domain data from the color difference detection result, and acquire image frequency distribution according to the image frequency domain data; The abnormal color region of the masterbatch is obtained according to the image frequency distribution, and the abnormal color difference position is obtained according to the abnormal color region of the masterbatch.

[0015] By adopting the above technical solution, by obtaining image frequency domain data from the color difference detection result, and obtaining the image frequency distribution according to the image frequency domain data, the color abnormal area of ​​the masterbatch can be accurately identified, and then the abnormal color difference position can be accurately obtained, thereby overcoming the problem of insufficient color difference detection accuracy caused by relying solely on spatial domain analysis in the traditional method, that is, by decomposing the frequency components of the masterbatch image through frequency domain analysis, it is possible to effectively distinguish normal areas from abnormal areas, especially for the recognition of slight color difference changes. By obtaining image frequency domain data, the analysis of the color components of the masterbatch can be further refined to ensure that every small color difference can be reflected in the frequency distribution. Furthermore, by obtaining the abnormal color area of ​​the masterbatch according to the image frequency distribution, the unevenly mixed area can be accurately located, avoiding the missed detection and false detection caused by noise interference or low-frequency component masking in the traditional method, and can effectively improve the detection sensitivity, especially when dealing with slight color differences in weak light environments. It shows significant advantages.

[0016] The second object of the invention is achieved by the following technical solutions: A masterbatch color detection device, the masterbatch color detection device comprising: A lighting environment acquisition module is used to acquire the environmental data to be detected, and obtain the ambient light intensity and ambient light direction from the environmental data to be detected; A light adjustment parameter acquisition module is used to acquire the color of the masterbatch to be detected, acquire the corresponding detection environment requirement data according to the color of the masterbatch to be detected, and compare the detection environment requirement data with the ambient light intensity and ambient light direction to obtain a light comparison result; A color difference detection module is used to adjust the environmental data to be detected according to the illumination comparison result, obtain a masterbatch detection image, perform spectral detection on the masterbatch detection image, and obtain a color difference detection result; The uniformity detection and positioning module is used to analyze the color difference detection result, obtain the abnormal color difference position according to the corresponding analysis result, and mark according to the abnormal color difference position.

[0017] By adopting the above technical solution, the detection consistency under different lighting conditions is ensured by obtaining the environmental data to be detected and extracting the ambient light intensity and ambient light direction from it. Then, based on the color information of the masterbatch to be detected, the corresponding detection environment requirement data is obtained, and it is compared with the actual ambient light conditions to obtain the light comparison result, so that the environmental data to be detected can be automatically adjusted, so that high-quality masterbatch detection images can be obtained under various lighting conditions; by performing spectral detection on the masterbatch detection image, the band spectral data of each pixel point can be accurately identified, and the color characteristics of the masterbatch can be further extracted. This process not only improves the speed of color difference detection, but also greatly improves the recognition accuracy and reliability. Then, by analyzing the image frequency domain data in the color difference detection result, the image frequency distribution is obtained, and the abnormal color difference position on the masterbatch surface is accurately identified and marked, which is convenient for the operator to perform subsequent processing.

[0018] The third objective of the present application is achieved through the following technical solutions: A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the masterbatch color detection method when executing the computer program.

[0019] The fourth objective of the present application is achieved through the following technical solutions: A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the masterbatch color detection method are implemented.

[0020] In summary, the present application includes at least one of the following beneficial technical effects: 1. It realizes accurate detection of masterbatch under different lighting conditions. By obtaining the environmental data to be detected and adjusting the environmental data to be detected according to the ambient light intensity and light direction, it ensures high-precision color difference detection even in complex production environments; 2. Combined with deep neural network, multi-band spectral analysis is performed on each pixel of the masterbatch detection image to achieve accurate diagnosis of color difference at the micron level, improving the accuracy and reliability of color recognition; 3. Through frequency domain analysis of color difference detection results, the abnormal color areas of masterbatch can be accurately identified and marked, so as to quickly locate the color uneven areas and assist in production process adjustment. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 is a flow chart of a masterbatch color detection method in one embodiment of the present application; Figure 2This is another implementation flow chart of the method for detecting the color of masterbatch in one embodiment of the present application; Figure 3 This is a flowchart of the implementation of step S20 of the method for detecting the color of masterbatch in one embodiment of the present application; Figure 4 This is a flowchart for implementing step S30 of the method for detecting the color of masterbatch in one embodiment of the present application; Figure 5 This is a flowchart of the implementation of step S40 of the method for detecting the color of masterbatch in one embodiment of the present application; Figure 6 This is a principle block diagram of a masterbatch color detection system in one embodiment of the present application; Figure 7 It is a schematic diagram of a device in an embodiment of the present application. DETAILED DESCRIPTION

[0022] The present application is further described in detail below in conjunction with the accompanying drawings.

[0023] In one embodiment, if Figure 1 As shown, the present application discloses a method for detecting color of masterbatch, which specifically comprises the following steps: S10: Acquire the environmental data to be detected, and acquire the ambient light intensity and the ambient light direction from the environmental data to be detected.

[0024] In this embodiment, the environmental data to be detected refers to the data of the external environment when the color difference and color uniformity detection is currently performed on a masterbatch of a certain color.

[0025] Specifically, when performing color detection on masterbatches of different colors, since different colors absorb light to different degrees, in order to reduce the interference caused by external irradiation light when detecting masterbatches of different colors, before visually detecting the color difference and uniformity of the masterbatch, the ambient light intensity, color and projection direction of the light are first obtained as the environmental data to be detected, so as to facilitate subsequent adjustments.

[0026] S20: Acquire the color of the masterbatch to be detected, acquire corresponding detection environment requirement data according to the color of the masterbatch to be detected, and compare the detection environment requirement data with the ambient light intensity and ambient light direction to obtain a light comparison result.

[0027] Specifically, according to the color of the masterbatch currently being tested, that is, the color of the masterbatch to be tested, when obtaining the masterbatch of this color for color testing, in order to reflect the best detection effect, the optimal external lighting conditions are used as the detection environment requirement data, and the light intensity, direction, color and other data in the detection environment requirement data are compared with the ambient light intensity and ambient light direction to obtain the difference between the current external lighting conditions and the detection environment requirement data, and then obtain the comparison result.

[0028] S30: adjusting the environmental data to be tested according to the illumination comparison result, acquiring a masterbatch test image, performing spectral test on the masterbatch test image, and obtaining a color difference test result.

[0029] Specifically, after obtaining the lighting comparison result, corresponding control instructions are generated according to the lighting comparison result, such as light intensity control instructions, lighting direction control instructions and / or lighting color control instructions, so as to adjust the lighting equipment, and then adjust the environment data to be detected to the detection environment requirement data corresponding to the masterbatch of that color.

[0030] Furthermore, an image of the finished masterbatch product to be inspected is captured by a corresponding photographing device as the masterbatch inspection image, and a spectral inspection is performed on the masterbatch inspection image to obtain the color difference of the finished masterbatch product as the color difference inspection result.

[0031] S40: Analyze the color difference detection result, obtain the abnormal color difference position according to the corresponding analysis result, and mark the abnormal color difference position.

[0032] Specifically, after obtaining the color difference detection result, the masterbatch detection image is analyzed according to the color difference detection result, and then whether the color difference and uniformity of the masterbatch meet the requirements is analyzed. If there are any places that do not meet the requirements, the corresponding abnormal color difference position is obtained from the image to be detected, and marked according to the abnormal color difference position for subsequent processing by relevant personnel.

[0033] In this embodiment, by acquiring the environmental data to be detected and extracting the ambient light intensity and ambient light direction therefrom, the detection consistency under different lighting conditions is ensured. Then, based on the color information of the masterbatch to be detected, the corresponding detection environment requirement data is obtained, and it is compared with the actual ambient light conditions to obtain the light comparison result, so that the environmental data to be detected can be automatically adjusted, so that high-quality masterbatch detection images can be obtained under various lighting conditions; by performing spectral detection on the masterbatch detection image, the band spectrum data of each pixel point can be accurately identified, and the color characteristics of the masterbatch can be further extracted. This process not only improves the speed of color difference detection, but also greatly improves the recognition accuracy and reliability. Then, by analyzing the image frequency domain data in the color difference detection result, the image frequency distribution is obtained, and the abnormal color difference position on the surface of the masterbatch is accurately identified and marked, which is convenient for the operator to perform subsequent processing.

[0034] In one embodiment, if Figure 2 As shown, before step S20, the masterbatch color detection method further includes: S201: Acquire historical masterbatch production data, and acquire masterbatch color data and corresponding abnormal color detection data from the historical masterbatch production data.

[0035] In this embodiment, the historical masterbatch production data refers to the data recorded when masterbatches of different colors were produced over a period of time in the past. The abnormal color detection data refers to the abnormal data detected when the color difference and uniformity of the masterbatch were tested in the past.

[0036] Specifically, when the color difference and uniformity of the masterbatch produced are tested historically, the data of the masterbatch of different colors after the test are recorded, including the color of the masterbatch and the abnormal color test data obtained by the test.

[0037] S202: Performing illumination tests under different illumination conditions on each color masterbatch color data, and obtaining abnormal color images corresponding to abnormal color detection data of each color masterbatch color data under different illumination conditions.

[0038] Specifically, each time a color masterbatch is tested in history, if an abnormality is detected, that is, abnormal color detection data is obtained, the masterbatch is subjected to a light test by changing different light intensity, color, light direction and other conditions, and the abnormal color image corresponding to each different light condition is recorded.

[0039] S203: Acquire abnormal color difference data in each abnormal color image, and acquire the lighting condition with the highest abnormal color difference data, and associate them with the masterbatch color data to obtain a corresponding color association model.

[0040] Specifically, each abnormal color image is associated with the corresponding lighting condition, and the position where the color difference and uniformity abnormality appear in the abnormal color image is obtained, and the display of the abnormal situation at the position is obtained as the abnormal color difference data, and the abnormal color difference data with the clearest display or the easiest computer to identify, that is, the highest abnormal color difference data, is selected, and its corresponding lighting condition is obtained. Further, the screened lighting conditions are associated with the corresponding masterbatch color data, and then the color association model is trained.

[0041] In one embodiment, if Figure 3 As shown, in step S20, the color of the masterbatch to be detected is obtained, and the corresponding detection environment requirement data is obtained according to the color of the masterbatch to be detected, which specifically includes: S21: Input the color of the masterbatch to be detected into the color association model to obtain detection lighting condition data.

[0042] Specifically, in order to obtain the optimal lighting condition for the color of the masterbatch to be detected during detection, the color of the masterbatch to be detected is input into the color association model, and the lighting condition to be detected is obtained according to the lighting conditions corresponding to masterbatches of different colors in the color association model.

[0043] S22: Generate detection environment requirement data according to the detection lighting condition data.

[0044] Specifically, after the detection lighting condition data is acquired, various types of lighting conditions, such as lighting intensity, lighting direction, and lighting color, are combined into the detection environment requirement data.

[0045] In one embodiment, if Figure 4 As shown, in step S30, the masterbatch detection image is subjected to spectral detection to obtain a color difference detection result, which specifically includes: S31: Obtaining the band spectrum data corresponding to each pixel from the masterbatch detection image, and extracting the masterbatch color features based on the band spectrum data.

[0046] Specifically, when shooting the masterbatch detection image, the color of the masterbatch is photographed by a high-resolution spectral camera to obtain the masterbatch detection image, and then the corresponding band spectral data is read from the image, and the multi-level features representing the color characteristics of the masterbatch are gradually extracted through the convolution layer as the color characteristics of the masterbatch.

[0047] S32: Analyze the color characteristics of the masterbatch of each pixel through a deep neural network to obtain a color difference detection result.

[0048] Specifically, the color characteristics of the masterbatch of each pixel are analyzed as a whole through the fully connected layer of the deep neural network, and the color difference judgment result is obtained according to the analysis result as the color difference detection result.

[0049] In one embodiment, if Figure 5 As shown, in step S40, the color difference detection result is analyzed, and the abnormal color difference position is obtained according to the corresponding analysis result, which specifically includes: S41: Obtain image frequency domain data from the color difference detection result, and obtain image frequency distribution according to the image frequency domain data.

[0050] Specifically, according to the color difference detection results, the image at the position where the color difference is greater than the preset value is obtained, and then the image is smoothed and filtered to remove the influence of noise, and then the local contrast enhancement technology is applied to highlight the slight color difference between the masterbatches. Next, the frequency domain analysis module intervenes to decompose the image signal to obtain the image frequency domain data, and the image frequency domain distribution is constructed based on the image frequency domain data.

[0051] S42: Obtain the color abnormality region of the masterbatch according to the image frequency distribution, and obtain the abnormal color difference position according to the color abnormality region of the masterbatch.

[0052] Specifically, the abnormal data inflection point is obtained according to the image frequency distribution, and the image area corresponding to the data inflection point is obtained as the masterbatch color abnormality area, and the position in the masterbatch detection image corresponding to the masterbatch color abnormality area is used as the abnormal color difference position.

[0053] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0054] In one embodiment, a masterbatch color detection device is provided, and the masterbatch color detection device corresponds to the masterbatch color detection method in the above embodiment. Figure 6 As shown, the masterbatch color detection device includes a light environment acquisition module, a light adjustment parameter acquisition module, a color difference detection module and a uniformity detection and positioning module. The functional modules are described in detail as follows: A lighting environment acquisition module is used to acquire the environmental data to be detected, and obtain the ambient light intensity and ambient light direction from the environmental data to be detected; The light adjustment parameter acquisition module is used to obtain the color of the masterbatch to be detected, obtain the corresponding detection environment requirement data according to the color of the masterbatch to be detected, and compare the detection environment requirement data with the ambient light intensity and ambient light direction to obtain the light comparison result; A color difference detection module is used to adjust the environmental data to be detected according to the illumination comparison result, obtain the masterbatch detection image, perform spectral detection on the masterbatch detection image, and obtain the color difference detection result; The uniformity detection and positioning module is used to analyze the color difference detection results, obtain the abnormal color difference position according to the corresponding analysis results, and mark the abnormal color difference position.

[0055] Optionally, the masterbatch color detection device further includes: A historical data acquisition module is used to acquire historical masterbatch production data, and acquire masterbatch color data and corresponding abnormal color detection data from the historical masterbatch production data; The historical data processing module is used to perform illumination tests under different illumination conditions on each color masterbatch color data, and obtain abnormal color images corresponding to abnormal color detection data of each color masterbatch color data under different illumination conditions; The model building module is used to obtain the abnormal color difference data in each abnormal color image and obtain the lighting conditions with the highest abnormal color difference data, and associate them with the masterbatch color data to obtain the corresponding color association model.

[0056] Optionally, the illumination adjustment parameter acquisition module includes: The model calculation submodule is used to input the color of the masterbatch to be detected into the color association model to obtain the detection light condition data; The environmental condition acquisition submodule is used to generate detection environment requirement data based on the detection lighting condition data.

[0057] Optionally, the color difference detection module includes: The spectral feature extraction submodule is used to obtain the band spectral data corresponding to each pixel from the masterbatch detection image, and extract the masterbatch color features based on the band spectral data; The color difference detection submodule is used to analyze the color characteristics of the masterbatch of each pixel through a deep neural network to obtain the color difference detection result.

[0058] Optionally, the uniformity detection and positioning module includes: The image frequency domain analysis submodule is used to obtain image frequency domain data from the color difference detection result, and obtain the image frequency distribution according to the image frequency domain data; The abnormal positioning submodule is used to obtain the abnormal color area of ​​the masterbatch according to the image frequency distribution, and obtain the abnormal color difference position according to the abnormal color area of ​​the masterbatch.

[0059] The specific definition of the masterbatch color detection device can be found in the definition of the masterbatch color detection method above, which will not be repeated here. Each module in the above-mentioned masterbatch color detection device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0060] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 7 As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a masterbatch color detection method is implemented.

[0061] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program: Acquire the environmental data to be detected, and obtain the ambient light intensity and the ambient light direction from the environmental data to be detected; Obtain the color of the masterbatch to be detected, obtain the corresponding detection environment requirement data according to the color of the masterbatch to be detected, and compare the detection environment requirement data with the ambient light intensity and ambient light direction to obtain the light comparison result; According to the illumination comparison result, the environmental data to be tested is adjusted, a masterbatch test image is obtained, and a spectrum test is performed on the masterbatch test image to obtain a color difference test result; The color difference detection results are analyzed, the abnormal color difference position is obtained according to the corresponding analysis results, and the abnormal color difference position is marked.

[0062] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented: Acquire the environmental data to be detected, and obtain the ambient light intensity and the ambient light direction from the environmental data to be detected; Obtain the color of the masterbatch to be detected, obtain the corresponding detection environment requirement data according to the color of the masterbatch to be detected, and compare the detection environment requirement data with the ambient light intensity and ambient light direction to obtain the light comparison result; According to the illumination comparison result, the environmental data to be tested is adjusted, a masterbatch test image is obtained, and a spectrum test is performed on the masterbatch test image to obtain a color difference test result; The color difference detection results are analyzed, the abnormal color difference position is obtained according to the corresponding analysis results, and the abnormal color difference position is marked.

[0063] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0064] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0065] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for detecting color of masterbatch, characterized in that: The masterbatch color detection method comprises: Acquire the environmental data to be detected, and acquire the ambient light intensity and the ambient light direction from the environmental data to be detected; Acquire the color of the masterbatch to be detected, acquire corresponding detection environment requirement data according to the color of the masterbatch to be detected, and compare the detection environment requirement data with the ambient light intensity and ambient light direction to obtain a light comparison result; The environmental data to be detected is adjusted according to the illumination comparison result, a masterbatch detection image is obtained, and a spectrum detection is performed on the masterbatch detection image to obtain a color difference detection result; The color difference detection result is analyzed, the abnormal color difference position is obtained according to the corresponding analysis result, and the abnormal color difference position is marked.

2. The masterbatch color detection method according to claim 1, characterized in that: Before obtaining the color of the masterbatch to be detected and obtaining the corresponding detection environment requirement data according to the color of the masterbatch to be detected, the masterbatch color detection method further includes: Acquire historical masterbatch production data, and acquire masterbatch color data and corresponding abnormal color detection data from the historical masterbatch production data; Performing illumination tests under different illumination conditions on each of the masterbatch color data, and obtaining abnormal color images corresponding to the abnormal color detection data of each of the masterbatch color data under different illumination conditions; Abnormal color difference data in each abnormal color image is obtained, and the lighting condition under which the abnormal color difference data is the highest is obtained, and the data is associated with the masterbatch color data to obtain a corresponding color association model.

3. The masterbatch color detection method according to claim 2, characterized in that: The step of obtaining the color of the masterbatch to be detected and obtaining the corresponding detection environment requirement data according to the color of the masterbatch to be detected specifically includes: Inputting the color of the masterbatch to be detected into the color association model to obtain detection light condition data; The detection environment requirement data is generated according to the detection lighting condition data.

4. The masterbatch color detection method according to claim 1, characterized in that: The performing spectral detection on the masterbatch detection image to obtain a color difference detection result specifically includes: Acquire the band spectrum data corresponding to each pixel from the masterbatch detection image, and extract the masterbatch color characteristics according to the band spectrum data; The color characteristics of the masterbatch of each pixel are analyzed by a deep neural network to obtain the color difference detection result.

5. The masterbatch color detection method according to claim 4, characterized in that: The analyzing the color difference detection result and obtaining the abnormal color difference position according to the corresponding analysis result specifically includes: Acquire image frequency domain data from the color difference detection result, and acquire image frequency distribution according to the image frequency domain data; The abnormal color region of the masterbatch is obtained according to the image frequency distribution, and the abnormal color difference position is obtained according to the abnormal color region of the masterbatch.

6. A masterbatch color detection device, characterized in that: The masterbatch color detection device comprises: A lighting environment acquisition module is used to acquire the environmental data to be detected, and obtain the ambient light intensity and ambient light direction from the environmental data to be detected; A light adjustment parameter acquisition module is used to acquire the color of the masterbatch to be detected, acquire the corresponding detection environment requirement data according to the color of the masterbatch to be detected, and compare the detection environment requirement data with the ambient light intensity and ambient light direction to obtain a light comparison result; A color difference detection module is used to adjust the environmental data to be detected according to the illumination comparison result, obtain a masterbatch detection image, perform spectral detection on the masterbatch detection image, and obtain a color difference detection result; The uniformity detection and positioning module is used to analyze the color difference detection result, obtain the abnormal color difference position according to the corresponding analysis result, and mark according to the abnormal color difference position.

7. The masterbatch color detection device according to claim 6, characterized in that: The masterbatch color detection device also includes: A historical data acquisition module, used to acquire historical masterbatch production data, and acquire masterbatch color data and corresponding abnormal color detection data from the historical masterbatch production data; A historical data processing module, used for performing illumination tests under different illumination conditions on each of the masterbatch color data, and obtaining abnormal color images corresponding to the abnormal color detection data of each of the masterbatch color data under different illumination conditions; The model building module is used to obtain abnormal color difference data in each abnormal color image, and obtain the lighting conditions under which the abnormal color difference data is the highest, and associate them with the masterbatch color data to obtain a corresponding color association model.

8. The masterbatch color detection device according to claim 7, characterized in that: The illumination adjustment parameter acquisition module includes: A model calculation submodule, used for inputting the color of the masterbatch to be detected into the color association model to obtain detection light condition data; The environmental condition acquisition submodule is used to generate the detection environment requirement data according to the detection lighting condition data.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the masterbatch color detection method according to any one of claims 1 to 5 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the masterbatch color detection method according to any one of claims 1 to 5 are implemented.

Images