RFID chip image anomaly detection method and system based on intelligent learning

Abstract

The invention relates to the technical field of RFID chip manufacturing, in particular to an RFID chip image anomaly detection method and system based on intelligent learning. The method comprises the following steps: acquiring a real-time RFID chip sampling image set, performing feature alignment based on a registration template, generating an average grey-scale map by using an alignment image set, and obtaining a chip edge mask image set by using an edge search algorithm; segmenting the edge mask image set of the RFID chip to obtain an effective edge mask variance image set of the RFID chip; integrating the variance image set to obtain a pre-generated variance image; acquiring field environment data of the RFID chip and performing sensitivity coefficient estimation to obtain an edge sensitivity coefficient; and performing convolution filtering smoothing processing on the pre-generated variance image to obtain a chip edge variance image, and constructing an RFID chip image anomaly detection model based on the edge variance image and the average grey-scale image. According to the invention, the detection accuracy and stability are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of RFID chip manufacturing, and in particular to an RFID chip image anomaly detection method and system based on intelligent learning. Background Art

[0002] For RFID abnormal area identification, traditional intelligent learning algorithms automatically generate average and variance maps based on standard samples. If the tension of the chip on site is unstable or the quality of the base paper is different, resulting in a slight deformation of the final image compared to the standard sample, the intelligent learning algorithm will cause a strict judgment (false alarm) of the image, especially when conducting quality inspection of transparent PET chips, a large number of false alarms will seriously affect the online production. The currently commonly used intelligent learning algorithm is to continuously collect qualified samples on site, and generate average and variance maps based on the brightness changes and stability changes of the samples themselves. The intelligent learning algorithm constructed in this mode can detect more obvious abnormalities such as ink spots, surface tape, dark dirt, etc., but it is easy to miss some abnormal areas with lighter colors and less obvious features. If the color difference range of the algorithm inspection is reduced, the corresponding false alarm rate will increase. Summary of the invention

[0003] Based on this, it is necessary for the present invention to provide an RFID chip image anomaly detection method and system based on intelligent learning to solve at least one of the above technical problems.

[0004] To achieve the above purpose, a method for detecting anomalies in RFID chip images based on intelligent learning comprises the following steps:

[0005] Step S1: obtaining a real-time RFID chip sampling image set; registering a feature template for the real-time RFID chip sampling image and performing image alignment based on the feature template to obtain an aligned image set, and calculating an average grayscale image of the aligned image set to obtain an average grayscale image; performing RFID chip edge search based on the aligned image set to obtain an RFID chip edge mask image set;

[0006] Step S2: performing edge mask image grayscale enhancement on the RFID chip edge mask image set to obtain an edge mask grayscale enhanced image set, and performing self-adaptive threshold segmentation on the edge mask grayscale enhanced image set to obtain an RFID chip effective edge mask image set;

[0007] Step S3: performing effective mask map union processing on the RFID chip effective edge mask image set to obtain the RFID chip mask union image, and integrating common edge features according to the RFID chip mask union image to obtain a pre-generated variance map;

[0008] Step S4: acquiring the field environment data of the RFID chip, and performing coil density evaluation based on the field environment data of the RFID chip, thereby obtaining the field environment coil density data; performing edge sensitivity coefficient estimation based on the field environment coil density data, thereby obtaining the edge sensitivity coefficient;

[0009] Step S5: Perform convolution filtering and smoothing processing on the pre-generated variance map according to the edge sensitivity coefficient to obtain the chip edge variance map, and build an RFID chip image anomaly detection model based on the chip edge variance map and the average grayscale map; perform sample image abnormal area detection on the real-time RFID chip sampling image set through the RFID chip image anomaly detection model to obtain the RFID chip abnormal area image set.

[0010] The present invention ensures that the detection system can timely reflect the actual situation on the production line by real-time acquisition of RFID chip images, and effectively improves the timeliness of detection. By aligning and calculating the average grayscale image of the real-time RFID chip sampling image set, the influence of factors such as illumination changes and angle deviations that occur during the image acquisition process on the image quality can be eliminated, thereby providing more stable and unified basic data for subsequent image analysis. By edge search and generating edge mask image sets, the contour features of the RFID chip can be effectively extracted, which is crucial for the precise positioning and defect detection of the chip. Further grayscale enhancement and adaptive threshold segmentation of the edge mask image can enhance the contrast of the edge information, so that more subtle abnormal features (such as defects with lighter colors and unclear contrast) can be more easily detected, reducing the risk of missed detection. By performing a union process on the effective mask image set, the edge information in multiple sampled images can be integrated, the noise influence in individual images can be eliminated, and a more stable and consistent pre-generated variance map can be obtained. The pre-generated variance map provides reliable basic data for subsequent abnormal detection, which can more accurately reflect the overall characteristics and changes of the image. Obtaining on-site environmental data and evaluating the coil density can effectively take into account the impact of environmental factors on the detection results. By evaluating the coil density, we can understand the extent to which the image quality may be affected. By calculating the edge sensitivity coefficient, we can quantify the edge response capability under different environmental conditions, and then adjust the subsequent image processing strategy to ensure that the algorithm can run stably under various conditions. Using the edge sensitivity coefficient to perform convolution filtering on the pre-generated variance map can effectively smooth the image, suppress the influence of random noise, and improve the clarity of edge features. The anomaly detection model constructed based on the processed chip edge variance map has higher accuracy, can timely and effectively identify abnormal areas in the real-time RFID chip image set, reduce the false alarm rate, and improve production efficiency. In summary, this series of steps combines real-time data acquisition, image processing algorithms and environmental factor analysis to form a complete set of RFID chip anomaly detection processes. This process not only improves the accuracy and stability of detection, but also effectively reduces the false alarms and missed detections that may occur in traditional algorithms in practical applications. Through refined processing and intelligent analysis, this technology can greatly improve the production quality of RFID chips and provide strong support for the development of the industry.

[0011] Optionally, step S1 specifically includes:

[0012] Step S11: Acquire a real-time RFID chip sampling image set;

[0013] Step S12: performing sample image set preprocessing on the real-time RFID chip sample image set, thereby obtaining the RFID chip sample image set;

[0014] Step S13: randomly selecting pictures from the real-time RFID chip sampling image set to obtain a random sampling image set, and performing feature registration based on the random sampling image set to obtain a feature template;

[0015] Step S14: performing residual image alignment on the real-time RFID chip sampling image set according to the feature template to obtain an aligned image set, and performing average grayscale image calculation on the aligned image set to obtain an average grayscale image;

[0016] Step S15: performing edge detection on the aligned image set to obtain an RFID chip edge feature image set;

[0017] Step S16: performing binary edge mask image conversion according to the RFID chip edge feature image set, thereby obtaining the RFID chip edge mask image set.

[0018] In the present invention, by preprocessing the real-time RFID chip sampling image set, noise or unnecessary interference factors in the original image can be removed, so that subsequent image processing is more accurate. Random image selection and feature registration help to obtain a more representative image template, ensure the accurate extraction of image features, and thus provide a high-quality data basis for subsequent image alignment and processing. The step of performing residual image alignment on the real-time RFID chip sampling image set minimizes the differences between different sampling images, thereby improving the accuracy of subsequent analysis, especially playing an important role in image registration and unified feature extraction. By calculating the average grayscale map, the overall brightness and contrast of the image can be standardized, so that images under different lighting conditions can also be effectively compared and analyzed. Edge detection can highlight the key features in the RFID chip image, help identify the outline and other important details of the chip, which is crucial for chip positioning and feature extraction. The binary edge mask image conversion step helps to further remove irrelevant background information and retain only edge features related to the RFID chip, thereby providing more accurate image data for subsequent analysis and processing of the chip.

[0019] Optionally, step S2 specifically includes:

[0020] Step S21: performing pixel binary statistics according to the RFID chip edge mask image set, thereby obtaining a high gradient change area image set and a low gradient change area image set;

[0021] Step S22: performing local adaptive histogram equalization on the image set in the high gradient change area, thereby obtaining a grayscale enhanced image set in the high gradient change area; performing edge contrast enhancement on the image set in the low gradient change area, thereby obtaining an enhanced image set in the low gradient change area;

[0022] Step S23: merging the high gradient change area grayscale enhanced image set and the low gradient change area enhanced image set to obtain an edge mask grayscale enhanced image set;

[0023] Step S24: performing adaptive threshold segmentation of functional regions according to the edge mask grayscale enhanced image set, thereby obtaining an effective edge mask image set of the RFID chip.

[0024] The present invention can accurately divide the high gradient change area and the low gradient change area in the image by performing pixel binary statistics on the RFID chip edge mask image set. This process can effectively distinguish the important edge information and the relatively gentle background area in the image, laying a good foundation for subsequent image processing. When the high gradient change area is subjected to local adaptive histogram equalization, the grayscale distribution of the image is enhanced, which helps to improve the visibility of the edge details in the image and makes the edge contour of the chip clearer. By performing edge contrast enhancement on the low gradient change area, the contrast of the relatively blurred or less detailed areas in the image can be effectively improved, so that the details of the overall image are enhanced, and the quality of the image is further improved. Then, the edge mask grayscale enhanced image set obtained after merging the images of the two types of areas helps to comprehensively reflect the advantageous information of the high gradient and low gradient areas, thereby obtaining a more balanced and accurate overall image, and providing good input conditions for the subsequent threshold segmentation processing. Through the adaptive threshold segmentation technology, the effective edge area of ​​the RFID chip can be accurately extracted from the enhanced image. This process can significantly improve the recognition effect of the effective edge in the image, ensuring that the positioning and reading of the RFID chip are more accurate. Overall, the design of this series of steps not only improves the grayscale and contrast of the image, but also ensures the processing effect of the RFID chip edge mask image set through multi-level and multi-angle image enhancement, thereby effectively improving the accuracy and stability of RFID chip recognition and reading.

[0025] Optionally, step S24 is specifically:

[0026] Step S241: performing local threshold calculation on the edge mask grayscale enhanced image set in the gradient change region, thereby obtaining local threshold data of the high gradient change region and local threshold data of the low gradient change region;

[0027] Step S242: performing functional region threshold segmentation on the edge mask grayscale enhanced image set according to the local threshold data of the high gradient change region, thereby obtaining a functional region threshold segmentation image set; performing boundary region threshold segmentation on the edge mask grayscale enhanced image set according to the local threshold data of the low gradient change region, thereby obtaining a boundary region threshold segmentation image set;

[0028] Step S243: performing an intersection operation on the boundary region threshold segmentation image set and the function region threshold segmentation image set, thereby obtaining a background entanglement function region image set;

[0029] Step S244: performing logical pixel merging on the background entanglement functional area image set and the functional area threshold segmentation image set, thereby obtaining an RFID chip effective edge mask image set.

[0030] The present invention performs local threshold calculation of gradient change region on edge mask grayscale enhanced image set, and can process different regions of high gradient change and low gradient change in the image respectively, which makes the threshold segmentation of the image more flexible and adaptable. High gradient region usually represents obvious edge or feature, while low gradient region may contain relatively smooth or background part. By calculating local thresholds for these two different regions respectively, it can ensure more refined segmentation in detail-rich region, and perform loose threshold processing in background or edge fuzzy region, thereby avoiding over-segmentation or omission while retaining key features. By performing functional region threshold segmentation on edge mask grayscale enhanced image set based on local threshold data of high gradient change region, the region representing the core functional part in the image can be extracted from the complex background, ensuring that the extracted functional region is of high quality and accurate. At the same time, using local threshold data of low gradient region to perform threshold segmentation on the boundary region of the image, the extraction effect of the edge part in the image is further enhanced, and the problem of misjudgment or missed judgment caused by image noise is avoided, thereby ensuring that the boundary region finally extracted is more accurate and clear. By performing the intersection operation on the functional area and the boundary area, the background interference and the blurred boundary area can be removed to obtain the background entangled functional area image set. This step helps to focus on the most representative and relevant parts of the image, further optimizes the image quality, and lays the foundation for the subsequent pixel merging operation. When performing the logical pixel merging of the background entangled functional area image set and the functional area threshold segmentation image set, the effective information of the two can be accurately fused to obtain the RFID chip effective edge mask image set. This step ensures the accuracy of the edge and functional area in the final image through intelligent pixel merging, removes redundant or unnecessary areas, and significantly improves the effectiveness and accuracy of the image. This result can not only provide high-quality image data in subsequent image analysis and recognition, but also improve the reliability and efficiency of the entire system in practical applications, especially in the precise positioning and recognition of RFID chips. It has important application value.

[0031] Optionally, step S3 specifically includes:

[0032] Step S31: performing binary statistics of pixels of the effective edge mask image set of the RFID chip, thereby obtaining binary data of pixels of the effective edge image set;

[0033] Step S32: performing a merging layer selection on the RFID chip effective edge mask image set according to the binary data of the pixel points of the effective edge image set, thereby obtaining the effective edge mask image set to be merged;

[0034] Step S33: setting geometric tolerance according to the binary data of the pixels in the valid edge image set, thereby obtaining the geometric tolerance data of the union set;

[0035] Step S34: performing effective mask image union processing on the effective edge mask image set to be united according to the union geometric tolerance data, so as to obtain the RFID chip mask union image;

[0036] Step S35: integrating common edge features according to the RFID chip mask and image union to obtain a pre-generated variance map.

[0037] The present invention can clearly identify and quantify the effective edge of the RFID chip by performing binary statistics of pixels on the effective edge mask image set, eliminate noise and interference, and improve the accuracy of image analysis. The binary data obtained provides an important quantitative basis for subsequent processing, making the characteristics of each edge clearer and helping to formulate a more reasonable image processing strategy. By selecting the union layer of the effective edge image set, the effective edge information in different images can be merged to form a more complete edge mask image set. This integration helps to extract more valuable information, can effectively reduce the interference of repeated information, and help to improve the efficiency of subsequent processing. By setting the geometric tolerance of the binary data of the pixels of the effective edge image set, the allowable range of edge features can be accurately regulated according to different manufacturing and detection requirements, thereby improving product consistency. The setting of the geometric tolerance enables the system to adapt to changes in different manufacturing processes and materials, and improves the adaptability of the RFID chip in different application scenarios. By processing the effective edge mask image set to be treated as a union, the effective mask image of the RFID chip can be further optimized, the clarity and availability of the image can be improved, and the accuracy of subsequent analysis and recognition can be improved. After the union processing of the effective mask image, the system can work at a higher accuracy, improving the performance of the entire detection process. By integrating the common edge features of the RFID chip mask union image, the key features of the RFID chip can be more comprehensively identified, providing a more representative sample. The final pre-generated variance map can not only reflect the stability of the edge features, but also provide a basis for subsequent quality control and anomaly detection, helping to discover potential problems in a timely manner.

[0038] Optionally, step S35 is specifically:

[0039] Step S351: extract edge structure features from the RFID chip mask union image to obtain image edge structure data;

[0040] Step S352: performing similarity calculation based on the image edge structure data, thereby obtaining edge structure similarity data;

[0041] Step S353: performing edge structure clustering calculation on the image edge structure data based on the edge structure similarity data, thereby obtaining edge structure clustering data, and performing common edge feature integration according to the edge structure clustering data, thereby obtaining common edge feature data;

[0042] Step S354: Calculate the edge feature variance according to the common edge feature data to obtain feature variance data, and visualize the feature variance data to obtain a pre-generated variance map.

[0043] The present invention can more accurately identify important information in an image and reduce the false recognition rate by extracting edge structural features. The extraction of edge features can reduce the amount of image data, which is convenient for subsequent processing and storage. Under conditions such as illumination changes and noise interference, the edge feature extraction algorithm is usually more robust and helps to improve the overall reliability of the system. Similarity data can help to classify similar images into the same category and improve the efficiency of classification. By calculating the similarity between images, relevant images can be quickly retrieved in a large-scale image library to improve user experience. By setting a similarity threshold, abnormal or unexpected images can be quickly identified, thereby improving the security of the system. Through clustering, similar edge features can be integrated to improve the representation ability and compactness of data. Through clustering, multiple similar features are classified into one category, which can reduce the complexity of subsequent calculations and improve processing speed. Cluster analysis can help identify potential patterns or structures in images and improve the depth and breadth of data analysis. Through the analysis of feature variance, the stability of features under different conditions can be evaluated, which helps to judge the reliability of features. Visualizing feature variance can intuitively display the dispersion of different features, which is convenient for subsequent decision-making and optimization. By analyzing the variance, we can optimize the feature selection process, select the most representative features, and improve system performance.

[0044] Optionally, step S4 specifically includes:

[0045] Step S41: Acquire the on-site environment data of the RFID chip;

[0046] Step S42: extracting RFID chip coil distribution features from the RFID chip field environment data, thereby obtaining RFID chip coil distribution data;

[0047] Step S43: performing regional coil density evaluation according to the RFID chip coil distribution data, thereby obtaining regional coil density data;

[0048] Step S44: spatially correlating the regional coil density data and the RFID chip edge feature image set, thereby obtaining coil density-edge feature correlation data;

[0049] Step S45: Estimating the sensitivity coefficient according to the coil density-edge feature association data, thereby obtaining the edge sensitivity coefficient.

[0050] The present invention collects on-site environmental data (such as temperature, humidity, metal interference, etc.), which can help understand the impact of the environment on RFID signal transmission, provide a basis for subsequent data analysis, ensure that the entire evaluation process has a basis, and thus improve the overall performance of the system. By extracting the coil distribution characteristics, the working state and signal propagation characteristics of the RFID chip under different environmental conditions can be identified, and feedback on coil design and deployment can be provided, which helps to optimize the layout of RFID equipment to reduce signal interference and improve recognition rate. Evaluating the density of coils can reveal the impact of different regions on signal strength and quality, provide a basis for resource allocation, help identify the signal difference between dense and sparse areas, and facilitate making corresponding adjustments in design to ensure the balance and reliability of the system. Through spatial correlation analysis, the mutual influence between regional coil density and environmental characteristics can be deeply understood, revealing the law of signal transmission in complex environments. Provide important context information for subsequent sensitivity coefficient estimation, making data analysis more targeted and effective. The estimation of sensitivity coefficients can quantify the impact of environmental factors on RFID chip performance and help identify key interference sources.

[0051] Optionally, step S42 is specifically:

[0052] Step S421: extracting RFID chip signal environment characteristics and physical environment characteristics according to the RFID chip field environment data, thereby obtaining RFID chip signal environment data and physical environment data;

[0053] Step S422: performing signal strength distribution statistics according to the RFID chip signal environment data, thereby obtaining the RFID chip signal strength distribution data;

[0054] Step S423: performing time-series correlation on the physical environment data and the RFID chip signal environment data to obtain physical environment-signal environment correlation data, and estimating the physical environment impact factor according to the physical environment-signal environment correlation data to obtain the physical environment impact factor;

[0055] Step S424: performing signal strength distribution correction on the RFID chip signal strength distribution data according to the physical environment influencing factors, thereby obtaining actual RFID chip signal strength distribution data;

[0056] Step S425: Estimating the RFID chip coil distribution according to the actual RFID chip signal strength distribution data, thereby obtaining the RFID chip coil distribution data.

[0057] The present invention can accurately obtain the real environment of signal propagation by extracting RFID chip signal environment data and physical environment characteristics. This provides basic data for subsequent analysis. Signal environment data helps to understand phenomena such as signal attenuation, reflection and multipath effects, and improves the ability of signal resolution. Statistical signal strength distribution can help researchers intuitively understand the intensity changes of RFID signals at different locations, so as to better design and optimize the RFID system. Through distribution statistics, areas with weak signals can be identified, providing a basis for subsequent optimization and signal enhancement measures. Through the temporal association of physical environment data and signal environment data, the specific impact of environmental changes on signal strength can be deeply understood. Estimating physical environment impact factors enables the system to quantify the impact of environmental factors on signal propagation, providing a basis for formulating corresponding improvement measures. Through the correction of physical environment impact factors, the accuracy of actual RFID signal strength distribution data can be significantly improved, thereby enhancing the reliability of the RFID system. The corrected signal strength data can effectively reduce the errors caused by environmental factors and improve the performance of the system in practical applications. Estimating the RFID chip coil distribution through actual signal strength distribution data can help designers optimize the coil layout and ensure the comprehensiveness of RFID system coverage and signal uniformity. Reasonable coil distribution can improve the recognition efficiency of RFID chips, reduce recognition time and cost, and improve the operating efficiency of the entire system.

[0058] Optionally, step S5 specifically includes:

[0059] Step S51: performing convolution filtering and smoothing processing on the pre-generated variance map according to the edge sensitivity coefficient, so as to obtain a chip edge variance map;

[0060] Step S52: extracting statistical features according to the chip edge variance map, thereby obtaining statistical feature data of the edge variance map;

[0061] Step S53: performing edge anomaly recognition on the chip edge variance map according to the edge variance map statistical feature data, thereby obtaining abnormal image edge data and normal image edge data;

[0062] Step S54: constructing an RFID chip image anomaly detection model according to the abnormal image edge data and the normal image edge data;

[0063] Step S55: using the RFID chip image anomaly detection model to perform sample image abnormality region detection on the real-time RFID chip sampling image set, thereby obtaining an RFID chip abnormal region image set.

[0064] The present invention can effectively remove random noise in the image and improve the clarity of the edge by performing convolution filtering on the pre-generated variance map. After smoothing, the features of the chip edge are more prominent, laying a foundation for subsequent feature extraction. By extracting the statistical features of the edge variance map, a quantitative description of the chip edge state can be obtained, and these data are helpful for subsequent anomaly detection. Through effective feature extraction, the amount of data to be processed is reduced, and the efficiency of subsequent processing is improved. Data analysis based on statistical features can accurately identify the abnormal situation of the chip edge, which is helpful for quickly locating the problem. Through the effective division of abnormal and normal data, the accuracy and reliability of the overall detection system are improved. By using abnormal and normal image edge data for training, the adaptability of the model to unknown data can be improved. After establishing an efficient detection model, real-time monitoring can be achieved, manual intervention can be reduced, and production efficiency can be improved. Through real-time abnormal area detection, potential problems can be quickly discovered and handled, and a large number of unqualified products can be prevented from entering the market. Through feedback on real-time detection results, the model is continuously optimized to improve the performance and accuracy of the overall detection system.

[0065] Optionally, the present specification also provides an RFID chip image anomaly detection system based on intelligent learning, which is used to execute the RFID chip image anomaly detection method based on intelligent learning as described above, and the RFID chip image anomaly detection system based on intelligent learning includes:

[0066] The edge search module is used to obtain a real-time RFID chip sampling image set; register a feature template for the real-time RFID chip sampling image and perform image alignment based on the feature template to obtain an aligned image set, and calculate an average grayscale image of the aligned image set to obtain an average grayscale image; perform RFID chip edge search based on the aligned image set to obtain an RFID chip edge mask image set;

[0067] A threshold segmentation module is used to perform edge mask image grayscale enhancement on the RFID chip edge mask image set, thereby obtaining an edge mask grayscale enhanced image set, and perform self-adaptive threshold segmentation on the edge mask grayscale enhanced image set, thereby obtaining an RFID chip effective edge mask image set;

[0068] The common edge feature integration module is used to perform effective mask map union processing on the RFID chip effective edge mask image set, so as to obtain the RFID chip mask union image, and perform common edge feature integration according to the RFID chip mask union image, so as to obtain a pre-generated variance map;

[0069] The edge sensitivity coefficient estimation module is used to obtain the field environment data of the RFID chip, and to perform coil density evaluation based on the field environment data of the RFID chip, thereby obtaining the field environment coil density data; and to perform edge sensitivity coefficient estimation based on the field environment coil density data, thereby obtaining the edge sensitivity coefficient;

[0070] The anomaly detection model building module is used to perform convolution filtering and smoothing processing on the pre-generated variance map according to the edge sensitivity coefficient to obtain the chip edge variance map, and build an RFID chip image anomaly detection model based on the chip edge variance map and the average grayscale map; the RFID chip image anomaly detection model is used to perform sample image abnormal area detection on the real-time RFID chip sampling image set to obtain the RFID chip abnormal area image set. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments thereof made with reference to the following drawings:

[0072] Figure 1 The figure is a schematic diagram of the steps of the RFID chip image anomaly detection method based on intelligent learning of the present invention;

[0073] Figure 2 Detailed step flow diagram of step S1 in the present invention;

[0074] Figure 3 Detailed step flow diagram of step S2 in the present invention;

[0075] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0076] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are 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 technicians in this field without creative work are within the scope of protection of the present invention.

[0077] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0078] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0079] To achieve this, please refer to Figures 1 to 3 The present invention provides an RFID chip image anomaly detection method based on intelligent learning, the method comprising the following steps:

[0080] Step S1: obtaining a real-time RFID chip sampling image set; registering a feature template for the real-time RFID chip sampling image and performing image alignment based on the feature template to obtain an aligned image set, and calculating an average grayscale image of the aligned image set to obtain an average grayscale image; performing RFID chip edge search based on the aligned image set to obtain an RFID chip edge mask image set;

[0081] In this embodiment, the image of the RFID chip is acquired in real time by a high-resolution camera or an RFID reading device, and the image sampling frequency is set to 10 frames per second to ensure clear capture of dynamic objects. The image processing algorithm is used to register the feature templates of these images. The template-based alignment technology is used to ensure that images under different viewing angles can be accurately aligned. After the images are aligned, an average grayscale image reflecting the overall brightness distribution is generated by calculating the average grayscale value of these images. Then, an edge detection algorithm (such as Canny edge detection) is used to find the edges of the aligned image set, and finally the chip edge mask image is extracted.

[0082] Step S2: performing edge mask image grayscale enhancement on the RFID chip edge mask image set to obtain an edge mask grayscale enhanced image set, and performing self-adaptive threshold segmentation on the edge mask grayscale enhanced image set to obtain an RFID chip effective edge mask image set;

[0083] In this embodiment, the obtained edge mask image set is subjected to grayscale enhancement by applying histogram equalization and gamma correction technology to improve the contrast and recognizability of the edge. For example, the gamma value of the image is adjusted to 2.2 to enhance the bright details. Afterwards, the Otsu method is used for adaptive threshold segmentation to obtain the effective edge mask image set of the RFID chip. This step ensures that the clear chip edge is extracted and the interference noise is filtered out.

[0084] Step S3: performing effective mask map union processing on the RFID chip effective edge mask image set to obtain the RFID chip mask union image, and integrating common edge features according to the RFID chip mask union image to obtain a pre-generated variance map;

[0085] In this embodiment, a logical "AND" operation is performed on the valid edge mask image set to form an RFID chip mask union image. In this process, by selecting an appropriate union operation rule, the edge information in all images is ensured to be integrated. At the same time, by extracting edge features (such as edge length, curvature, etc.), the common edge features of each mask are calculated. The final pre-generated variance map will show the edge changes of the RFID chip in different images, and the image statistical analysis tools (such as mean and standard deviation calculation) are used to quantify the stability and variability of the edge.

[0086] Step S4: acquiring the field environment data of the RFID chip, and performing coil density evaluation based on the field environment data of the RFID chip, thereby obtaining the field environment coil density data; performing edge sensitivity coefficient estimation based on the field environment coil density data, thereby obtaining the edge sensitivity coefficient;

[0087] In this embodiment, sensors are deployed to collect on-site environmental data, such as temperature, humidity, signal strength, etc. Combined with the electromagnetic field strength of the area where the RFID chip is located, the coil density is evaluated by a known algorithm (such as an electromagnetic field simulation model). Assuming that there are 5 RFID readers in a certain area, the coil density can be set to 5 / area (in square meters). Based on the coil density data, the edge sensitivity coefficient is calculated, for example, using linear regression analysis to obtain the edge sensitivity coefficient value as a parameter for subsequent processing.

[0088] Step S5: Perform convolution filtering and smoothing processing on the pre-generated variance map according to the edge sensitivity coefficient to obtain a chip edge variance map, and construct an RFID chip image anomaly detection model based on the chip edge variance map; perform sample image abnormal area detection on the real-time RFID chip sampling image set through the RFID chip image anomaly detection model to obtain an RFID chip abnormal area image set.

[0089] In the present embodiment, convolution filtering is applied to the pre-generated variance map based on the edge sensitivity coefficient obtained. Suitable convolution kernels (such as 3x3 Gaussian filters) are selected to smooth the image and reduce the influence of noise, thereby improving the significance of edge features. After filtering, a chip edge variance map is obtained. Then, a deep learning model (such as convolutional neural network) is used to build an RFID chip image anomaly detection model. By training the model, a real-time RFID chip sampling image set is input, and the model generates a grayscale threshold range map. If the grayscale of some regions is not within the grayscale threshold range after the new image is aligned, such a region is an abnormal region, so as to detect the abnormal region in the image, and finally output the RFID chip abnormal region image set, so as to provide data support for subsequent analysis and processing.

[0090] Optionally, step S1 specifically includes:

[0091] Step S11: Acquire a real-time RFID chip sampling image set;

[0092] In this embodiment, a high-definition camera or industrial camera is used to capture images of objects equipped with RFID chips through a real-time image acquisition device. The device needs to be configured to be able to capture high-quality images under different lighting conditions and have a high resolution (such as 1080p or higher resolution) to ensure that the details of the surface of the RFID chip and its surroundings can be clearly captured. In order to ensure real-time performance, the image acquisition device can be connected to a computer or embedded processing system to transmit the image data stream to the data processing system in real time. During the image acquisition process, the system should timestamp each frame of the image for sequential processing during subsequent image analysis. Suppose that in a logistics warehouse, goods equipped with RFID tags are moving through a conveyor belt. Use an industrial camera installed above the conveyor belt to acquire RFID chip images at a speed of 10 frames per second. Each captured image can be stored in PNG format for use in subsequent image processing stages.

[0093] Step S12: performing sample image set preprocessing on the real-time RFID chip sample image set, thereby obtaining the RFID chip sample image set;

[0094] In this embodiment, the acquired image set is preprocessed to enhance the image quality and improve the effect of subsequent feature extraction. The preprocessing steps include denoising, normalization and cropping. Denoising uses Gaussian blur or median filtering algorithm to reduce random noise in the image. Normalization adjusts the pixel value of the image to a uniform range (such as between 0 and 1) to avoid the influence of image brightness differences on subsequent processing. Cropping is to remove the background part of the image that is not related to the RFID chip and only retain the RFID chip area. The preprocessed image can be unified into a fixed size (such as 256x256 pixels), and ensure that the area of ​​the RFID chip in the image is in the center position for subsequent analysis. For example, in the captured image, there may be other interferences or overexposed areas around the RFID chip. Denoising is performed using a 3x3 Gaussian filter to reduce grayscale fluctuations in the image; then histogram equalization is applied to improve image contrast and enhance the visibility of the RFID chip surface.

[0095] Step S13: randomly selecting pictures from the real-time RFID chip sampling image set to obtain a random sampling image set, and performing feature registration based on the random sampling image set to obtain a feature template;

[0096] In this embodiment, in order to reduce the computational complexity and improve the representativeness of feature extraction, a portion of images are randomly selected from the preprocessed image set (including N frames of images). Assume that the image set contains 1000 frames of images, and randomly select 200 frames from them for feature extraction. The randomly selected images can be realized by a random number generator to ensure that the distribution of the selected images in the entire image set is uniform. After the image is selected, a feature matching algorithm (such as SIFT, SURF, etc.) is used for feature registration. The purpose of feature registration is to match similar feature points in these images to generate a template feature set for subsequent image alignment and analysis. For example, 200 frames are randomly selected from a 1000-frame image set, and the key feature points are extracted from these images using the SIFT algorithm by calculating the similarity between the images. Then, these feature points are matched to generate a feature template. This template will be used for subsequent image alignment and analysis.

[0097] Step S14: performing residual image alignment on the real-time RFID chip sampling image set according to the feature template to obtain an aligned image set, and performing average grayscale image calculation on the aligned image set to obtain an average grayscale image;

[0098] In this embodiment, the obtained feature template is used to perform image registration or alignment on the remaining images. Through a feature matching algorithm, such as an image registration method based on the RANSAC algorithm, the transformation matrix between the images is calculated to ensure that the position of the RFID chip in each frame image is aligned with the template. The image alignment process may involve geometric transformations such as rotation, scaling, and translation, with the goal of making the RFID chip area in each frame image highly coincident with the feature template. The average grayscale image of the aligned image can be calculated as an evaluation criterion for the alignment quality. Assuming that the template image is a sample image of the RFID chip that has been feature registered, the transformation matrix is ​​calculated and applied through the RANSAC algorithm and applied to other sampled images. The aligned image will present a clear structure of the RFID chip area, which is convenient for subsequent grayscale calculation and feature extraction.

[0099] Step S15: performing edge detection on the aligned image set to obtain an RFID chip edge feature image set;

[0100] In this embodiment, the aligned image set is subjected to edge detection, and a classical edge detection algorithm, such as Canny edge detection, Sobel operator or Laplacian operator, is used. By performing gradient calculation on the image, the region with large grayscale changes in the image, especially the edge portion of the RFID chip, is extracted. Edge detection helps to highlight important features in the image, such as the outline of the RFID chip, metal pins, label printing and other details. In practical applications, the edge detection algorithm can be optimized by adjusting the threshold to obtain the best edge feature map. For example, the aligned RFID chip image is processed using the Canny edge detection algorithm, and the low threshold is set to 50 and the high threshold is set to 150, thereby effectively extracting the edge information of the RFID chip. The edge image will show the outline of the chip and other obvious features, which is convenient for further analysis.

[0101] Step S16: performing binary edge mask image conversion according to the RFID chip edge feature image set, thereby obtaining the RFID chip edge mask image set.

[0102] In this embodiment, the edge feature map is converted into an edge mask map by binarizing the edge detection result. Binarization can be achieved by setting a fixed threshold or an automatic threshold algorithm (such as the Otsu algorithm), and the edge portion in the image is set to white and the non-edge portion is set to black. The obtained edge mask image set can effectively identify the edge area of ​​the RFID chip for subsequent morphological analysis, size detection, etc. The binary mask image is of great significance for feature extraction, morphological analysis and image segmentation in the processing process. For example, the Otsu algorithm is used to automatically calculate the optimal threshold for the edge detection image, and then the edge area is set to white and the non-edge area is set to black to form a clear edge mask image set. These mask images can help the system accurately identify the shape and structure of the RFID chip, ensuring that subsequent processing is more accurate.

[0103] Optionally, step S2 specifically includes:

[0104] Step S21: performing pixel binary statistics according to the RFID chip edge mask image set, thereby obtaining a high gradient change area image set and a low gradient change area image set;

[0105] In this embodiment, the gradient calculation is performed on each pixel in the RFID chip edge mask image set, and the gradient value is obtained by calculating the difference between adjacent pixels. According to the set gradient threshold, the pixels in the image are divided into "high gradient change area" and "low gradient change area". The high gradient area usually corresponds to the part with obvious edges or rapid changes in the image, such as the contact point or structural details of the RFID chip; the low gradient area is the part of the image that changes slowly or is relatively flat, such as the background area or the large internal plane area. Through this operation, the image is divided into two sets: one is the image set of high gradient change area, and the other is the image set of low gradient change area.

[0106] Step S22: performing local adaptive histogram equalization on the image set in the high gradient change area, thereby obtaining a grayscale enhanced image set in the high gradient change area; performing edge contrast enhancement on the image set in the low gradient change area, thereby obtaining an enhanced image set in the low gradient change area;

[0107] In this embodiment, different image enhancement processes are performed on the image set of high gradient change area and the image set of low gradient change area respectively to improve the image quality and facilitate subsequent analysis. For the image set of high gradient change area, the local adaptive histogram equalization (Adaptive Histogram Equalization, AHE) method is used to enhance the contrast of the image. The core idea of ​​the AHE algorithm is to divide the image into multiple small areas (for example, local windows), calculate the histogram in each local area and perform equalization processing. Unlike the traditional global histogram equalization, AHE can make local adjustments to the brightness distribution of different areas, thereby improving the detail performance of high gradient areas. The size of each window can be set (for example, 16x16 or 32x32 pixels), and the pixel grayscale value of each window can be adjusted according to the local histogram, so that the detail area in the image is more prominent, especially at the tiny structure and edge of the RFID chip. For the image set of low gradient change area, the edge contrast enhancement technology is used. The purpose of this step is to improve the clarity of the image by increasing the contrast of the edge part in the image. Common edge contrast enhancement methods include edge enhancement techniques based on the Laplacian operator or Laplacian of Gaussian (LoG). The edge information of the image is extracted through a filtering algorithm, and the edge detection is performed on the image using an operator such as the Laplacian operator, and then the contrast of the edge portion is enhanced to highlight the details. For example, the brightness of edge pixels can be adjusted using a weighted average method, and the details of the image can be enhanced by increasing the contrast of these areas. First, the low-frequency part (background) of the image is extracted, and then the contrast of the low-gradient area is increased by contrast stretching or gamma correction, so that the details and edges on the surface of the RFID chip are displayed more clearly.

[0108] Step S23: merging the high gradient change area grayscale enhanced image set and the low gradient change area enhanced image set to obtain an edge mask grayscale enhanced image set;

[0109] In this embodiment, the grayscale enhanced image set of the high gradient change area and the enhanced image set of the low gradient change area are merged. An image weighted fusion method is adopted, such as a simple weighted summation or a fusion algorithm based on pixel similarity. A merging coefficient can be defined (such as 0.7 for images in high gradient change areas and 0.3 for images in low gradient change areas) to generate an edge mask grayscale enhanced image set. For example, the merged image can clearly show that the clarity of the edge area is improved, and the details of the overall image are richer, which is helpful for subsequent processing.

[0110] Step S24: performing adaptive threshold segmentation of functional regions according to the edge mask grayscale enhanced image set, thereby obtaining an effective edge mask image set of the RFID chip.

[0111] In this embodiment, adaptive threshold segmentation of functional regions is performed based on the edge mask grayscale enhanced image set. Otsu's method or an adaptive segmentation algorithm based on region growing can be used here to dynamically select a threshold value based on the grayscale distribution of the image. In implementation, the grayscale histogram of each image is first calculated, and then the optimal threshold is selected for segmentation based on the principle of maximizing the inter-class variance. Finally, a set of effective edge mask images of the RFID chip is obtained. For example, if the processed image segments the effective edge area of ​​the RFID chip and successfully suppresses the background noise, the effective edge mask image is shown to have a clear outline, which is suitable for further analysis and application.

[0112] Optionally, step S24 is specifically:

[0113] Step S241: performing local threshold calculation on the edge mask grayscale enhanced image set in the gradient change region, thereby obtaining local threshold data of the high gradient change region and local threshold data of the low gradient change region;

[0114] In this embodiment, the image set after grayscale enhancement is processed by an edge detection algorithm (such as Sobel operator, Canny operator, etc.) to calculate the gradient value of each pixel. In this process, the gradient amplitude of each pixel in the image is first obtained. Then, a gradient threshold is set, and the area with a larger gradient amplitude is calculated and classified as a high gradient change area, and the area with a smaller gradient amplitude is a low gradient change area. The high gradient change area is usually the edge or detail part of the object, while the low gradient change area is the background or flat area. Next, the local threshold value of each area is determined by local threshold calculation to adapt to the image characteristics of different areas. For example, in an image containing an RFID chip, the gradient change of the edge is large, while the gradient change of a flat area such as the background is small. In this way, two data sets can be obtained: local threshold data of high gradient change area and local threshold data of low gradient change area.

[0115] Step S242: performing functional region threshold segmentation on the edge mask grayscale enhanced image set according to the local threshold data of the high gradient change region, thereby obtaining a functional region threshold segmentation image set; performing boundary region threshold segmentation on the edge mask grayscale enhanced image set according to the local threshold data of the low gradient change region, thereby obtaining a boundary region threshold segmentation image set;

[0116] In this embodiment, based on the calculated local threshold data of the high gradient change area, these data are used to perform threshold segmentation on the edge mask grayscale enhanced image to distinguish between functional areas and boundary areas. The local threshold data of the high gradient change area is used to perform binarization on the image to extract the functional area in the image. The functional area usually contains the target object in the image, such as the identification area or pattern of the RFID chip. In this process, by setting an appropriate threshold range, the target object can be extracted and separated from the background. The local threshold data of the low gradient change area is used to perform binarization to segment the boundary area. The boundary area usually refers to a relatively flat or less detailed part of the image, such as the background area, or the edge part around the target object. By analyzing the gradient amplitude of the image, an appropriate threshold can be set, for example, the threshold is set to 50. If the gradient value of a pixel is greater than 50, it is considered to be a high gradient change area, usually corresponding to the edge part of the object. The image is binarized using this gradient threshold to extract the functional area. For example, the identification area of ​​an RFID chip contains many complex details, and the gradient values ​​corresponding to these details are relatively high. Therefore, after binarization, the external structure and details of the chip can be successfully extracted. For low gradient change areas, a lower gradient threshold can be set, such as setting the threshold to 10. If the gradient value of a pixel is less than 10, the area is considered to be a low gradient change area, which usually corresponds to the background part of the image. By setting a low gradient threshold, the background area in the image is extracted. These areas are usually flat and have little change, such as the white background part in the RFID chip image, or other background areas of the image.

[0117] Step S243: performing an intersection operation on the boundary region threshold segmentation image set and the function region threshold segmentation image set, thereby obtaining a background entanglement function region image set;

[0118] In this embodiment, the obtained boundary area threshold segmentation image set and the functional area threshold segmentation image set are subjected to intersection operation. The purpose of the intersection operation is to obtain the part of the image that belongs to both the functional area and the boundary area. The intersection operation is performed pixel by pixel on the binarization results of the functional area and the boundary area, and the "1" (pixels indicating the existence of an object or area) in the two areas are compared. If a pixel is "1" in both areas, it means that the pixel belongs to both the functional area and the boundary area. For example, in the image of an RFID chip, these areas usually represent the outer frame or circuit part of the chip.

[0119] Step S244: performing logical pixel merging on the background entanglement functional area image set and the functional area threshold segmentation image set, thereby obtaining an RFID chip effective edge mask image set.

[0120] In this embodiment, a logical operation (such as an "AND" operation or an "OR" operation) is used to merge the obtained background entangled functional area image set and the functional area threshold segmentation image set at the pixel level. The purpose is to eliminate the erroneous segmentation results caused by background interference and retain the real valid area in the image. For example, after the intersection operation, the obtained background entangled functional area image set may contain some erroneous edge parts, but after the logical operation pixel merging, the pixels containing only the valid functional area can be retained. For example, in the image of the RFID chip, after merging, the final image will clearly show the effective area of ​​the chip, while removing irrelevant background or noise. Finally, through processing, the effective edge mask image set of the RFID chip is obtained, which can effectively provide accurate image boundary data for subsequent image analysis or recognition. This step plays a key role in the final segmentation and target extraction of the image.

[0121] Optionally, step S3 specifically includes:

[0122] Step S31: performing binary statistics of pixels of the effective edge mask image set of the RFID chip, thereby obtaining binary data of pixels of the effective edge image set;

[0123] In this embodiment, the effective edge mask image set of the RFID chip is subjected to binary pixel statistics to count the number of white pixels (value 1) and black pixels (value 0) of the effective edge. This process not only helps to identify the number of effective edges, but also provides basic data for subsequent steps. For example, if the number of white pixels of the effective edge in a mask image is 5,000 and the number of black pixels is 15,000, it means that the effective edge feature of the mask image is more obvious.

[0124] Step S32: performing a merging layer selection on the RFID chip effective edge mask image set according to the binary data of the pixel points of the effective edge image set, thereby obtaining the effective edge mask image set to be merged;

[0125] In this embodiment, according to the obtained pixel binary data, the effective edge mask image set of the RFID chip is combined. Select images with a higher effective edge pixel density and stack them layer by layer. To ensure the accuracy of the data, a threshold can be set (for example, only images with more than 3000 effective edge pixels can be included in the union calculation). Finally, a new effective edge mask image set to be combined is formed to facilitate the subsequent geometric tolerance setting. For example, if there are three mask images, two of which have effective edge pixels exceeding the threshold, their union will retain all white pixels, while black pixels will be removed.

[0126] Step S33: setting geometric tolerance according to the binary data of the pixels in the valid edge image set, thereby obtaining the geometric tolerance data of the union set;

[0127] In this embodiment, the geometric tolerance is set according to the binary data of the pixel points of the effective edge image set. The geometric tolerance mainly refers to the error range allowed in the manufacturing and detection process. Parameters can be set according to the shape characteristics (such as width, thickness, etc.) of the effective edge, for example, the maximum tolerance is set to 2 pixels and the minimum tolerance is set to 1 pixel. Using these tolerance data, a geometric tolerance data set can be created to provide a reference for subsequent mask image processing. For example, if the actual width of a certain effective edge is 10 pixels, then after the geometric tolerance is set, the effective edge will allow an error between 8 and 12 pixels.

[0128] Step S34: performing effective mask image union processing on the effective edge mask image set to be united according to the union geometric tolerance data, thereby obtaining an RFID chip mask union image;

[0129] In this embodiment, the obtained geometric tolerance data is used to process the set of valid edge mask images to be merged. According to the geometric tolerance setting, it is determined whether the geometric shape of the valid edge in each mask image meets the requirements. If it meets the requirements, the valid edges of the mask images are merged to form a union image of the RFID chip mask. For example, if there are multiple mask images, and the valid edge of a mask image is within the geometric tolerance range, its valid edge will be superimposed on the union image, thereby enhancing the overall characteristics of the image.

[0130] Step S35: integrating common edge features according to the RFID chip mask and image union to obtain a pre-generated variance map.

[0131] In this embodiment, the common edge features are integrated according to the RFID chip mask and the union image. The process includes edge detection (such as Canny edge detection algorithm) on the union image to extract the common edge features. According to the shape and distribution of the common edge, a pre-generated variance map is generated for subsequent analysis and optimization. If a specific edge feature is found to appear frequently in multiple images, the feature can be focused on for further quality control and optimization. For example, if the variance value of a certain edge in the pre-generated variance map is lower than the set threshold, it indicates that the edge feature is relatively stable during the production process and is worth retaining.

[0132] Optionally, step S35 is specifically:

[0133] Step S351: extract edge structure features from the RFID chip mask union image to obtain image edge structure data;

[0134] In this embodiment, the mask image of the RFID chip is processed. The Canny edge detection algorithm can be used to extract the edge structure in the image. By setting appropriate high and low thresholds, the Canny algorithm can effectively identify obvious edges and form an edge image. Then, the extracted edge image is subjected to morphological processing, such as corrosion and expansion, to eliminate noise and enhance edge features. Ultimately, the generated edge structure data will contain the coordinate information and intensity value of the edge to facilitate subsequent similarity calculations.

[0135] Step S352: performing similarity calculation based on the image edge structure data, thereby obtaining edge structure similarity data;

[0136] In this embodiment, after completing the edge structure feature extraction, the next task is to perform similarity calculation. The edge structure similarity between different images can be evaluated using Euclidean distance or cosine similarity. For example, the edge structure data of two images are selected, converted into vector form, and then their Euclidean distance is calculated. If the distance is less than a set threshold, it is considered that the two images are similar in edge structure. The result of the similarity calculation will be saved in the form of a matrix, in which each element represents the similarity value between the two images.

[0137] Step S353: performing edge structure clustering calculation on the image edge structure data based on the edge structure similarity data, thereby obtaining edge structure clustering data, and performing common edge feature integration according to the edge structure clustering data, thereby obtaining common edge feature data;

[0138] In this embodiment, after obtaining the edge structure similarity data, a clustering algorithm is used to analyze it. For example, the K-means clustering algorithm can be applied to cluster the edge similarity matrix. The number of clusters K is set, and the appropriate K value can be selected according to the elbow rule. After the clustering is completed, the edge structure clustering data will be obtained, including the information of the center point and member images of each cluster. Subsequently, based on these clustering results, the common edge features can be integrated to identify the edge features that appear repeatedly in multiple images. This process involves feature selection techniques, such as using principal component analysis (PCA) to reduce feature dimensions and enhance computational efficiency.

[0139] Step S354: Calculate the edge feature variance according to the common edge feature data to obtain feature variance data, and visualize the feature variance data to obtain a pre-generated variance map.

[0140] In this embodiment, feature variance calculation is performed according to the common edge feature data. By calculating the variance of each common edge feature, its stability in different images is analyzed. The numpy library can be used to calculate the variance and generate corresponding statistical data. Subsequently, the feature variance data is displayed in the form of a heat map using visualization tools such as Matplotlib to form a pre-generated variance map. This figure can intuitively show which features have a high degree of variation in the image set, thereby providing a basis for subsequent feature selection or classification.

[0141] Optionally, step S4 specifically includes:

[0142] Step S41: Acquire the on-site environment data of the RFID chip;

[0143] In this embodiment, appropriate environmental monitoring equipment is selected, such as temperature and humidity sensors, light sensors, and electromagnetic sensors. These devices are placed at the location where the RFID chip is used and photographed to collect environmental data in real time. The frequency of data collection should be set to once every 5 minutes to ensure the timeliness of the data. During the data collection process, the data is transmitted to the central processing system via a wireless network. The data format can be selected in JSON format to facilitate subsequent processing and analysis. In addition, a data quality monitoring mechanism should be established to ensure the accuracy and reliability of the data, for example, a threshold is set to filter out abnormal values.

[0144] Step S42: extracting RFID chip coil distribution features from the RFID chip field environment data, thereby obtaining RFID chip coil distribution data;

[0145] In this embodiment, the collected environmental data is analyzed using a machine learning algorithm. First, the environmental data is preprocessed, including normalization and denoising. Next, a clustering algorithm (such as K-means) is applied to identify the coil distribution characteristics of the RFID chip. By mapping the coil distribution onto a two-dimensional plane, a visualization tool can be used to generate a coil distribution map showing the relative position and density between the coils. Finally, the coil distribution data is output, including the center coordinates, radius, and relative density value of each coil, which will provide the necessary basis for subsequent steps.

[0146] Step S43: performing regional coil density evaluation according to the RFID chip coil distribution data, thereby obtaining regional coil density data;

[0147] In this embodiment, the coil distribution data is divided into different regions. A fixed region size (e.g., 10m x 10m) can be set, and the number and distribution of RFID chip coils in each region are counted. The coil density of the region is calculated using the formula: the density is equal to the area of ​​the region divided by the number of coils in the region. The results are then stored in a database, and a coil density distribution map is generated to visualize the coil distribution of the region.

[0148] Step S44: spatially correlating the regional coil density data and the RFID chip edge feature image set, thereby obtaining coil density-edge feature correlation data;

[0149] In this embodiment, the edge features are combined with the coil density data, and the relationship between the coil density and the edge features is evaluated using a spatial statistical method (such as spatial regression analysis). By calculating the correlation coefficient, a coil density-edge feature association graph is generated. In implementation, Python's SciPy library can be used for data analysis, and Matplotlib library can be used for data visualization to facilitate observation of the relationship between the two.

[0150] Step S45: Estimating the sensitivity coefficient according to the coil density-edge feature association data, thereby obtaining the edge sensitivity coefficient.

[0151] In this embodiment, according to the coil density-edge feature association data, a regression analysis method (such as linear regression or multiple regression) is used to estimate the edge sensitivity coefficient. First, a mathematical model is established, and the coil density, edge features and other variables that may affect the sensitivity are included in the model. The model is fitted using the training data to obtain regression coefficients, which will be used as estimates of the sensitivity coefficient. The statsmodels library in R language or Python can be used for model construction and evaluation, and the cross-validation method can be used to improve the accuracy of the model. Finally, the numerical value of the sensitivity coefficient and its corresponding statistical significance are output to help subsequent analysis and decision-making.

[0152] Optionally, step S42 is specifically:

[0153] Step S421: extracting RFID chip signal environment characteristics and physical environment characteristics according to the RFID chip field environment data, thereby obtaining RFID chip signal environment data and physical environment data;

[0154] In this embodiment, the collected RFID signal data includes signal strength, noise level, transmission frequency, etc. Then, the physical environment data is obtained through the data collected by the environmental sensor (such as temperature, humidity, light and object occlusion). The signal feature extraction adopts time domain and frequency domain analysis methods, including Fourier transform, etc., to obtain the spectral characteristics of the signal. At the same time, through statistical analysis, the influence of different environmental factors on signal strength is identified. Finally, a comprehensive data set of RFID chip signal environment data and physical environment data is formed.

[0155] Step S422: performing signal strength distribution statistics according to the RFID chip signal environment data, thereby obtaining the RFID chip signal strength distribution data;

[0156] In this embodiment, a statistical analysis of the signal strength distribution is performed based on the collected signal strength data. The signal strength can be divided into multiple intervals using methods such as a histogram or a distribution diagram, and the signal strength frequency in each interval is calculated. The concentrated areas of signal strength are identified by using a clustering algorithm (such as K-means clustering) and marked as "strong signal" or "weak signal" areas. These statistical results are displayed in a visual manner, for example, using a heat map to represent the signal strength distribution at different locations. This process helps identify the distribution characteristics of RFID signals in different physical environments.

[0157] Step S423: performing time-series correlation on the physical environment data and the RFID chip signal environment data to obtain physical environment-signal environment correlation data, and estimating the physical environment impact factor according to the physical environment-signal environment correlation data to obtain the physical environment impact factor;

[0158] In this embodiment, previously collected physical environment data (such as temperature changes, humidity fluctuations, etc.) and RFID signal data (such as signal strength changes) are used for time series correlation analysis. The relationship between signal changes and physical environment changes is compared using time series analysis technology. For example, the correlation coefficient calculation method is used to analyze the correlation between physical environment changes and signal strength changes in different time periods. Then, based on the analysis results, the main physical environment factors that affect the signal strength are extracted. For example, under high humidity conditions, the signal strength may be reduced, and finally the physical environment-signal environment correlation data is formed.

[0159] Step S424: performing signal strength distribution correction on the RFID chip signal strength distribution data according to the physical environment influencing factors, thereby obtaining actual RFID chip signal strength distribution data;

[0160] In this embodiment, the estimated physical environment impact factor is used to correct the signal strength distribution data of the RFID chip. For example, if it is found that the high humidity conditions in a certain area will cause the signal strength to drop by 10%, this compensation factor is added to the actual RFID signal strength distribution data. A linear regression model or a polynomial fitting method is used to implement this correction to ensure that the corrected signal strength data is more consistent with the actual situation. Ultimately, the generated actual RFID chip signal strength distribution data can more accurately reflect the signal status under environmental influences.

[0161] Step S425: Estimating the RFID chip coil distribution according to the actual RFID chip signal strength distribution data, thereby obtaining the RFID chip coil distribution data.

[0162] In this embodiment, the distribution of the RFID chip coils is estimated based on the actual RFID chip signal strength distribution data obtained. The signal strength of the unmeasured area is estimated based on the signal strength data of the known position through spatial interpolation technology (such as Kriging interpolation or inverse distance weighted method). Based on the corrected actual RFID signal strength distribution data, the distribution of the RFID chip coils is estimated using an inversion algorithm (such as genetic algorithm or particle swarm optimization). By analyzing the changes in signal strength in different areas, the position and number of the coils are inferred.

[0163] Optionally, step S5 specifically includes:

[0164] Step S51: performing convolution filtering and smoothing processing on the pre-generated variance map according to the edge sensitivity coefficient, so as to obtain a chip edge variance map;

[0165] In this embodiment, the pre-generated variance map is convoluted and filtered according to the edge sensitivity coefficient (ESC) to eliminate noise and enhance the clarity of the chip edge. The pre-generated variance map is convolved with the edge sensitivity coefficient and smoothed using a Gaussian filter. By selecting a suitable convolution kernel (such as a Gaussian kernel of 3\times 33×3 or 5\times 55×5) for convolution calculation, noise is reduced and the edge detection accuracy of the image is improved. After the processing is completed, the generated chip edge variance map can effectively highlight the edge features and provide a high-quality data basis for subsequent steps.

[0166] Step S52: extracting statistical features according to the chip edge variance map, thereby obtaining statistical feature data of the edge variance map;

[0167] In this embodiment, the obtained chip edge variance map is subjected to statistical feature extraction, specifically including mean, variance, maximum value, minimum value, standard deviation, etc. These features can reflect the overall characteristics and distribution of the chip edge. These statistical features can be quickly calculated using Python's NumPy library. For example, np.mean() is used to calculate the mean, and np.var() is used to calculate the variance. At the same time, the edge intensity distribution can also be visualized by drawing a histogram for analysis. The extracted statistical feature data provides an important numerical basis for subsequent anomaly detection.

[0168] Step S53: performing edge anomaly recognition on the chip edge variance map according to the edge variance map statistical feature data, thereby obtaining abnormal image edge data and normal image edge data;

[0169] In this embodiment, based on the extracted statistical feature data, a threshold method or a method based on machine learning is used to identify abnormal edges. An adaptive threshold can be set, and when the edge variance exceeds the threshold, it is judged to be abnormal. In terms of implementation method, the edge feature data can first be divided into two categories: normal and abnormal using a k-means clustering algorithm, and then the features are trained and tested using a classifier (such as a random forest, a support vector machine, etc.). Finally, the identified abnormal edge data and normal edge data are stored separately for subsequent analysis and processing.

[0170] Step S54: constructing an RFID chip image anomaly detection model according to the abnormal image edge data and the normal image edge data;

[0171] In this embodiment, based on the collected normal and abnormal image edge data, a suitable algorithm (such as a convolutional neural network in deep learning) is selected to build an abnormality detection model. The TensorFlow or PyTorch framework can be used to design a network structure, including a convolutional layer, a pooling layer, and a fully connected layer. The training data of the model should include a large number of images with normal and abnormal edges marked to improve the classification accuracy of the model. Through cross-validation and hyperparameter tuning, the model performance is gradually optimized to have good detection capabilities.

[0172] Step S55: using the RFID chip image anomaly detection model to perform sample image abnormality region detection on the real-time RFID chip sampling image set, thereby obtaining an RFID chip abnormal region image set.

[0173] In this embodiment, the constructed abnormality detection model is used to process the real-time collected RFID chip image set. By performing edge detection and feature extraction on each frame of the image, it is input into the trained model to detect the abnormal area. The real-time image can be quickly processed using image stream processing technology (such as OpenCV). The abnormal area information output by the model will be marked on the image, and an abnormal area image set will be generated to facilitate subsequent further analysis and verification. Combined with the real-time monitoring system, it can respond to and handle potential anomalies in a timely manner, improving the overall reliability and security of the RFID chip.

[0174] Optionally, the present specification also provides an RFID chip image anomaly detection system based on intelligent learning, which is used to execute the RFID chip image anomaly detection method based on intelligent learning as described above, and the RFID chip image anomaly detection system based on intelligent learning includes:

[0175] The edge search module is used to obtain a real-time RFID chip sampling image set; register a feature template for the real-time RFID chip sampling image and perform image alignment based on the feature template to obtain an aligned image set, and calculate an average grayscale image of the aligned image set to obtain an average grayscale image; perform RFID chip edge search based on the aligned image set to obtain an RFID chip edge mask image set;

[0176] A threshold segmentation module is used to perform edge mask image grayscale enhancement on the RFID chip edge mask image set, thereby obtaining an edge mask grayscale enhanced image set, and perform self-adaptive threshold segmentation on the edge mask grayscale enhanced image set, thereby obtaining an RFID chip effective edge mask image set;

[0177] The common edge feature integration module is used to perform effective mask map union processing on the RFID chip effective edge mask image set, so as to obtain the RFID chip mask union image, and perform common edge feature integration according to the RFID chip mask union image, so as to obtain a pre-generated variance map;

[0178] The edge sensitivity coefficient estimation module is used to obtain the field environment data of the RFID chip, and to perform coil density evaluation based on the field environment data of the RFID chip, thereby obtaining the field environment coil density data; and to perform edge sensitivity coefficient estimation based on the field environment coil density data, thereby obtaining the edge sensitivity coefficient;

[0179] The anomaly detection model building module is used to perform convolution filtering and smoothing processing on the pre-generated variance map according to the edge sensitivity coefficient to obtain the chip edge variance map, and build an RFID chip image anomaly detection model based on the chip edge variance map and the average grayscale map; the RFID chip image anomaly detection model is used to perform sample image abnormal area detection on the real-time RFID chip sampling image set to obtain the RFID chip abnormal area image set.

[0180] The RFID chip image anomaly detection system based on intelligent learning of the present invention can implement any one of the RFID chip image anomaly detection methods based on intelligent learning of the present invention, and is used to combine the operation and signal transmission medium between various modules to complete the RFID chip image anomaly detection method based on intelligent learning. The internal modules of the system cooperate with each other, thereby improving the accuracy and stability of detection.

[0181] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0182] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A method for detecting anomalies in RFID chip images based on intelligent learning, characterized in that: The following steps are involved: Step S1: Acquire a real-time RFID chip sampling image set; Registering feature templates for real-time RFID chip sampling images and performing image alignment based on the feature templates to obtain an aligned image set, and calculating an average grayscale image of the aligned image set to obtain an average grayscale image; Find the edge of the RFID chip according to the aligned image set, so as to obtain the RFID chip edge mask image set; Step S2: performing edge mask image grayscale enhancement on the RFID chip edge mask image set to obtain an edge mask grayscale enhanced image set, and performing self-adaptive threshold segmentation on the edge mask grayscale enhanced image set to obtain an RFID chip effective edge mask image set; Step S3: performing effective mask map union processing on the RFID chip effective edge mask image set to obtain the RFID chip mask union image, and integrating common edge features according to the RFID chip mask union image to obtain a pre-generated variance map; Step S4: acquiring the field environment data of the RFID chip, and performing coil density evaluation based on the field environment data of the RFID chip, thereby obtaining the field environment coil density data; performing edge sensitivity coefficient estimation based on the field environment coil density data, thereby obtaining the edge sensitivity coefficient; Step S5: Perform convolution filtering and smoothing processing on the pre-generated variance map according to the edge sensitivity coefficient to obtain the chip edge variance map, and build an RFID chip image anomaly detection model based on the chip edge variance map and the average grayscale map; perform sample image abnormal area detection on the real-time RFID chip sampling image set through the RFID chip image anomaly detection model to obtain the RFID chip abnormal area image set.

2. The RFID chip image anomaly detection method based on intelligent learning according to claim 1 is characterized in that: Step S1 is specifically as follows: Step S11: Acquire a real-time RFID chip sampling image set; Step S12: performing sample image set preprocessing on the real-time RFID chip sample image set, thereby obtaining the RFID chip sample image set; Step S13: randomly selecting pictures from the real-time RFID chip sampling image set to obtain a random sampling image set, and performing feature registration based on the random sampling image set to obtain a feature template; Step S14: performing residual image alignment on the real-time RFID chip sampling image set according to the feature template to obtain an aligned image set, and performing average grayscale image calculation on the aligned image set to obtain an average grayscale image; Step S15: performing edge detection on the aligned image set to obtain an RFID chip edge feature image set; Step S16: performing binary edge mask image conversion according to the RFID chip edge feature image set, thereby obtaining the RFID chip edge mask image set.

3. The RFID chip image anomaly detection method based on intelligent learning according to claim 1 is characterized in that: Step S2 is specifically as follows: Step S21: performing pixel binary statistics according to the RFID chip edge mask image set, thereby obtaining a high gradient change area image set and a low gradient change area image set; Step S22: performing local adaptive histogram equalization on the high gradient change area image set, thereby obtaining a high gradient change area grayscale enhanced image set; Performing edge contrast enhancement on the low gradient change region image set, thereby obtaining a low gradient change region enhanced image set; Step S23: merging the high gradient change area grayscale enhanced image set and the low gradient change area enhanced image set to obtain an edge mask grayscale enhanced image set; Step S24: performing adaptive threshold segmentation of functional regions according to the edge mask grayscale enhanced image set, thereby obtaining an effective edge mask image set of the RFID chip.

4. The RFID chip image anomaly detection method based on intelligent learning according to claim 3 is characterized in that: Step S24 is specifically as follows: Step S241: performing local threshold calculation on the edge mask grayscale enhanced image set in the gradient change region, thereby obtaining local threshold data of the high gradient change region and local threshold data of the low gradient change region; Step S242: performing functional region threshold segmentation on the edge mask grayscale enhanced image set according to the local threshold data of the high gradient change region, thereby obtaining a functional region threshold segmentation image set; performing boundary region threshold segmentation on the edge mask grayscale enhanced image set according to the local threshold data of the low gradient change region, thereby obtaining a boundary region threshold segmentation image set; Step S243: performing an intersection operation on the boundary region threshold segmentation image set and the function region threshold segmentation image set, thereby obtaining a background entanglement function region image set; Step S244: performing logical pixel merging on the background entanglement functional area image set and the functional area threshold segmentation image set, thereby obtaining an RFID chip effective edge mask image set.

5. The RFID chip image anomaly detection method based on intelligent learning according to claim 1 is characterized in that: Step S3 is specifically as follows: Step S31: performing binary statistics of pixels of the effective edge mask image set of the RFID chip, thereby obtaining binary data of pixels of the effective edge image set; Step S32: performing a merging layer selection on the RFID chip effective edge mask image set according to the binary data of the pixel points of the effective edge image set, thereby obtaining the effective edge mask image set to be merged; Step S33: setting geometric tolerance according to the binary data of the pixels in the valid edge image set, thereby obtaining the geometric tolerance data of the union set; Step S34: performing effective mask image union processing on the effective edge mask image set to be united according to the union geometric tolerance data, so as to obtain the RFID chip mask union image; Step S35: integrating common edge features according to the RFID chip mask and image union to obtain a pre-generated variance map.

6. The RFID chip image anomaly detection method based on intelligent learning according to claim 5 is characterized in that: Step S35 is specifically as follows: Step S351: extract edge structure features from the RFID chip mask union image to obtain image edge structure data; Step S352: performing similarity calculation based on the image edge structure data, thereby obtaining edge structure similarity data; Step S353: performing edge structure clustering calculation on the image edge structure data based on the edge structure similarity data, thereby obtaining edge structure clustering data, and performing common edge feature integration according to the edge structure clustering data, thereby obtaining common edge feature data; Step S354: Calculate the edge feature variance according to the common edge feature data to obtain feature variance data, and visualize the feature variance data to obtain a pre-generated variance map.

7. The RFID chip image anomaly detection method based on intelligent learning according to claim 1 is characterized in that: Step S4 is specifically as follows: Step S41: Acquire the on-site environment data of the RFID chip; Step S42: extracting RFID chip coil distribution features from the RFID chip field environment data, thereby obtaining RFID chip coil distribution data; Step S43: performing regional coil density evaluation according to the RFID chip coil distribution data, thereby obtaining regional coil density data; Step S44: spatially correlating the regional coil density data and the RFID chip edge feature image set, thereby obtaining coil density-edge feature correlation data; Step S45: Estimating the sensitivity coefficient according to the coil density-edge feature association data, thereby obtaining the edge sensitivity coefficient.

8. The method for detecting anomalies in RFID chip images based on intelligent learning according to claim 7, characterized in that: Step S42 is specifically as follows: Step S421: extracting RFID chip signal environment characteristics and physical environment characteristics according to the RFID chip field environment data, thereby obtaining RFID chip signal environment data and physical environment data; Step S422: performing signal strength distribution statistics according to the RFID chip signal environment data, thereby obtaining the RFID chip signal strength distribution data; Step S423: performing time-series correlation on the physical environment data and the RFID chip signal environment data to obtain physical environment-signal environment correlation data, and estimating the physical environment impact factor according to the physical environment-signal environment correlation data to obtain the physical environment impact factor; Step S424: performing signal strength distribution correction on the RFID chip signal strength distribution data according to the physical environment influencing factors, thereby obtaining actual RFID chip signal strength distribution data; Step S425: Estimating the RFID chip coil distribution according to the actual RFID chip signal strength distribution data, thereby obtaining the RFID chip coil distribution data.

9. The RFID chip image anomaly detection method based on intelligent learning according to claim 1, characterized in that: Step S5 is specifically as follows: Step S51: performing convolution filtering and smoothing processing on the pre-generated variance map according to the edge sensitivity coefficient, so as to obtain a chip edge variance map; Step S52: extracting statistical features according to the chip edge variance map, thereby obtaining statistical feature data of the edge variance map; Step S53: performing edge anomaly recognition on the chip edge variance map according to the edge variance map statistical feature data, thereby obtaining abnormal image edge data and normal image edge data; Step S54: constructing an RFID chip image anomaly detection model according to the abnormal image edge data and the normal image edge data; Step S55: using the RFID chip image anomaly detection model to perform sample image abnormality region detection on the real-time RFID chip sampling image set, thereby obtaining an RFID chip abnormal region image set.

10. An RFID chip image anomaly detection system based on intelligent learning, characterized in that: The method for detecting anomalies in RFID chip images based on intelligent learning according to claim 1 comprises: The edge search module is used to obtain a real-time RFID chip sampling image set; register a feature template for the real-time RFID chip sampling image and perform image alignment based on the feature template to obtain an aligned image set, and calculate an average grayscale image of the aligned image set to obtain an average grayscale image; perform RFID chip edge search based on the aligned image set to obtain an RFID chip edge mask image set; A threshold segmentation module is used to perform edge mask image grayscale enhancement on the RFID chip edge mask image set, thereby obtaining an edge mask grayscale enhanced image set, and perform self-adaptive threshold segmentation on the edge mask grayscale enhanced image set, thereby obtaining an RFID chip effective edge mask image set; The common edge feature integration module is used to perform effective mask map union processing on the RFID chip effective edge mask image set, so as to obtain the RFID chip mask union image, and perform common edge feature integration according to the RFID chip mask union image, so as to obtain a pre-generated variance map; The edge sensitivity coefficient estimation module is used to obtain the field environment data of the RFID chip, and to perform coil density evaluation based on the field environment data of the RFID chip, thereby obtaining the field environment coil density data; and to perform edge sensitivity coefficient estimation based on the field environment coil density data, thereby obtaining the edge sensitivity coefficient; The anomaly detection model building module is used to perform convolution filtering and smoothing processing on the pre-generated variance map according to the edge sensitivity coefficient to obtain the chip edge variance map, and build an RFID chip image anomaly detection model based on the chip edge variance map and the average grayscale map; the RFID chip image anomaly detection model is used to perform sample image abnormal area detection on the real-time RFID chip sampling image set to obtain the RFID chip abnormal area image set.

Images