Refreshing method for driving image of electronic display equipment

Abstract

The invention provides an image refreshing method for driving electronic display equipment, which relates to the technical field related to electronic display, and comprises the following steps: inputting a target image into an image detection model to obtain M pre-detection results and N results to be subjected to secondary detection; constructing a pre-detection sequence and a secondary recognition image set; obtaining a first vision, a second vision and a third detection sequence; obtaining first-level, second-level and third difference scores; pre-constructing a difference degree analysis model, obtaining a difference degree analysis value of the secondary identification image set, and obtaining P second detection results when the difference degree analysis value is greater than a preset second threshold value; according to the M + P result and a third threshold judgment result, a corresponding driving instruction is generated, a control signal of the corresponding driving instruction is converted into a corresponding voltage waveform, the voltage waveform is transmitted to the electronic paper display screen, and the electronic paper display screen refreshes and updates display content according to the corresponding waveform; energy consumption is reduced, overall refreshing efficiency is improved, and user experience is improved.

Description

Technical Field

[0001] The present application relates to a technical field related to electronic display, and in particular to a method for driving an image refresh of an electronic display device. Background Art

[0002] Electronic paper display is a special type of electronic display device with a unique display refresh mechanism, which is a passive refresh mechanism. The system will refresh the screen to display a new image only when the image data needs to be updated. Initially, electronic paper display can only display in black and white. Due to the small amount of data transmitted, it can be globally refreshed to display new images. The overall image update time is short and does not occupy a large amount of transmission channel resources. At present, electronic paper display has developed from the initial black and white display to support multiple color display, such as three colors, four colors and six colors. This display is mostly used in e-books, book illustrations or static advertisements, which have high requirements for the color of electronic paper display images. As a result, the image transmission data increases and occupies a large amount of transmission channel resources. The traditional electronic paper display hardware is not suitable for the transmission needs of today's multi-color images. At this stage, the global refresh efficiency is mainly improved by upgrading and transforming the hardware such as the main control chip and display driver chip. This process involves complex hardware research and development, which will not only increase costs, but also may cause compatibility issues. In addition, it will still occupy a large amount of transmission channel data, consume a lot of energy, and affect the user experience. Summary of the invention

[0003] The present application provides a method for driving an electronic display device to refresh an image, aiming to solve the problems of high cost and high energy consumption in the prior art when driving image refresh, and the impact on user experience due to compatibility issues.

[0004] In a first aspect disclosed in the present application, a method for driving an image refresh of an electronic display device is provided, wherein the electronic display device includes an electronic paper display screen, and the method includes:

[0005] Acquire an image to be displayed, determine whether the image to be displayed is a non-black and white image, and obtain a target image, wherein the image to be displayed is a static image formed by a combination of text and / or pictures; input the target image into an image segmentation unit of an image detection model, obtain K target segmented images and image position identifiers, input the K target segmented images into a hash algorithm detection unit of an image detection model, and obtain hash values ​​of the K target segmented images through a BMH hash algorithm; traverse the image position identifier, calculate the Hamming distance between the hash value of the target segmented image under each image position identifier and the hash value of the current segmented image, map the Hamming distance to the image position identifier one by one, perform a pre-inspection on the Hamming distance through a preset first threshold, and obtain M pre-inspection results. The invention discloses a method for preparing a pre-inspection detection sequence, wherein the image position identifiers of the N results to be re-inspected are defined as the secondary detection position identifiers, and the secondary detection position identifiers are arranged in ascending order according to their corresponding Hamming distances to obtain a pre-inspection detection sequence, and the current segmented images under the secondary detection position identifiers are combined with the results to be re-inspected to form paired segmented images to obtain a secondary recognition image set; the difference detection is performed on each paired segmented image in the secondary recognition image set by using a histogram method, a structural similarity index, and a feature point matching method, and the secondary detection position identifiers are arranged in ascending order according to their corresponding detection results to obtain a first detection sequence, a second detection sequence, and a third detection sequence, respectively. The first detection sequence is used as a benchmark, and the second detection position identifier is traversed to calculate the total number of steps of the ranking improvement in the first detection sequence to obtain a first difference score. The first detection sequence is used as a benchmark, and the second detection position identifier is traversed to calculate the total number of steps of the ranking improvement in the second detection sequence to obtain a second difference score. The second detection sequence is used as a benchmark, and the second detection position identifier is traversed to calculate the total number of steps of the ranking improvement in the third detection sequence to obtain a third difference score. The first difference score, the second difference score, and the third difference score are synchronized to the difference analysis model to obtain the difference analysis value of the secondary recognition image set, wherein the difference analysis model is based on a multivariate regression model and uses three difference scores as as input, and take the difference analysis value as output; judge that the difference analysis value is greater than a preset second threshold value, eliminate repeated images, and obtain P secondary detection results, P≤N; judge whether the result of M+P is less than a preset third threshold value, if so, drive the main control chip to generate a local refresh drive instruction, drive the display driver chip to convert the control signal of the instruction into a corresponding voltage waveform, drive the electronic paper display screen to perform local image refresh according to the voltage waveform corresponding to the instruction, and display the target image; if not, drive the main control chip to generate a global refresh drive instruction, drive the display driver chip to convert the control signal of the instruction into a corresponding voltage waveform, drive the electronic paper display screen to perform global image refresh according to the voltage waveform corresponding to the instruction, and display the target image.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0007] The image to be displayed is obtained, and it is determined that the image to be displayed is not a black-and-white image, and the target image is obtained, which can avoid unnecessary image difference judgment, divert the execution of the refresh method of the image driving the electronic display device, and improve the overall refresh efficiency; the target image is input into the image detection model, K target segmentation images are obtained, and a pre-inspection is performed to obtain M pre-inspection results and N results to be secondary detected, and the target segmentation image that needs to be subjected to multivariate visual detection is quickly identified, the accuracy of image detection is improved, the amount of calculation of the system is reduced, and the overall refresh efficiency is improved; a pre-inspection detection sequence and a secondary recognition image set are constructed, and further image difference recognition is performed in the secondary recognition atlas, which has a clear target and a narrow scope, and improves the detection efficiency; a first detection sequence, a second detection sequence, and a third detection sequence are obtained, and the differences between the paired segmented images are more fully captured, thereby enhancing the comprehensiveness of the detection; through the first difference degree score, the second difference degree score, and the third difference degree score , reflects the difference degree of paired segmented images under different visual detection technologies, and is helpful to comprehensively evaluate the overall difference of paired segmented images in the secondary recognition image set; through the difference analysis model, the first difference score, the second difference score and the third difference score are subjected to multivariate regression comprehensive judgment, and the scattered difference scores are combined to obtain the difference analysis value of the secondary recognition image set, thereby improving the judgment accuracy of paired segmented images in the secondary recognition image set; judging that the difference analysis value is greater than the preset second threshold, P second detection results are obtained; judging whether the result of M+P is less than the third threshold, and driving the master control chip to generate the corresponding driving instruction through the judgment result, driving the display driving chip to convert the control signal of the corresponding driving instruction into the corresponding voltage waveform, driving the electronic paper display screen to perform image refresh according to the refresh strategy corresponding to the corresponding driving instruction, updating the displayed image, and minimizing unnecessary refresh operations. The present invention uses a simpler, more convenient and less costly method to minimize the occupation of transmission channel resources and thus reduce resource consumption, thereby improving the overall efficiency of driving the refresh of the electronic paper display screen image. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1 A schematic flow chart of a method for driving an electronic display device to refresh an image provided in an embodiment of the present application.

[0009] Figure 2 This is a diagram of the internal structure of a system for driving an image refresh of an electronic display device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0010] The embodiments of the present application provide a method for driving an electronic display device to refresh an image, thereby solving the problems of the prior art in which the image refresh driving method has high cost, high energy consumption, and a negative impact on user experience due to compatibility issues.

[0011] After introducing the basic principles of the present application, various non-limiting implementation methods of the present application will be specifically introduced below in conjunction with the accompanying drawings of the specification. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0012] The electronic display device includes an electronic paper display screen, and in the application of driving the refresh of the electronic paper display screen image, a main control chip and a display driver chip are included, the main control chip and the display driver chip are integrated on a circuit board, and are electrically connected to the electronic paper display screen for data transmission and control, wherein the main control chip is responsible for processing input information and generating corresponding drive instructions according to the analysis results of the input information, and the display driver chip is responsible for generating corresponding voltage waveforms from the control signals of the drive instructions, transmitting the generated corresponding voltage waveforms to the electronic paper display screen through physical lines, driving the electronic paper display screen to refresh, thereby updating the displayed image. Improving the refresh efficiency by upgrading and transforming the hardware such as the main control chip and the display driver chip involves complex hardware research and development, higher costs and possible compatibility issues. The method provided in this application aims to improve the overall efficiency of driving the refresh of the electronic paper display screen image by improving the efficiency of image difference detection, reducing resource consumption and minimizing the occupied transmission channel resources in a simpler, more convenient and less costly method.

[0013] like Figure 1 As shown, an embodiment of the present application provides a method for driving an image refresh of an electronic display device, wherein the electronic display device includes an electronic paper display screen, and the method includes:

[0014] Step S100: obtaining an image to be displayed, and determining whether the image to be displayed is a non-black and white image, wherein the image to be displayed is an image that has been preprocessed to meet the application of an electronic paper display screen, the preprocessing includes image denoising, image resolution adjustment, and image dithering processing, the image dithering processing includes a black and white mode and a non-black and white mode, and marking the dithering mode, the non-black and white mode includes a three-color dithering mode, a four-color dithering mode, a five-color dithering mode, and a six-color dithering mode, and the image to be displayed is a static image formed by a combination of text and / or pictures;

[0015] If yes, determine that the image to be displayed is a non-black and white image, and obtain the target image.

[0016] If not, it is determined that the image to be displayed is a black and white image, the master control chip is driven to generate a global refresh drive instruction, the display driver chip is driven to convert the control signal of the instruction into a corresponding voltage waveform, and the electronic paper display screen is driven to perform global image refresh according to the voltage waveform corresponding to the instruction to display the target image.

[0017] In the embodiment of the present application, the image display refresh of the electronic paper display screen is jointly driven by the main control chip and the display driver chip. The acquired target image is transmitted to the main control chip, and the difference between the target image and the current image is detected. The preset refresh strategy is executed according to the detection result, and the main control chip is driven to generate a drive instruction according to the corresponding refresh strategy, and the display driver chip is driven to convert the control signal of the drive instruction into a corresponding voltage waveform, and the corresponding voltage waveform is transmitted to the electronic paper display screen through a physical line, and the electronic paper display screen is driven to refresh the corresponding area according to the voltage waveform to update the displayed image. The image to be displayed can be obtained from multiple sources, and the image can be transmitted from the web page end, and the stored image resources can be obtained from the server end in the web page environment, or the image can be obtained through operations such as uploading, which can be in JPEG, PNG and other formats, and marked as the image to be displayed. On the e-paper display image processing tool on the web page or mobile phone APP, according to the application of the e-paper display, including the application scenario of the e-paper display, the resolution of the e-paper display and the different color display modes of the electronic display (supporting black and white, three-color, four-color, five-color or six-color display), the image to be displayed is first denoised, the image resolution is adjusted to be consistent with the resolution of the e-paper display, and then the image is jittered. You can choose to transfer it to the main control chip via USB; you can also choose to transfer the image from the WeChat applet, and you can access the album or camera to obtain the image to be displayed. After the image is jittered, the main control chip supports Bluetooth function and communicates with the WeChat applet through the Bluetooth module. The main control chip and the display driver chip are integrated on a circuit board, and the chip is usually installed on the motherboard of the device. Obtain the preprocessed image to be displayed, and determine whether the image to be displayed is a black-and-white image or a multi-color image according to the jitter pattern marked on the display image. If it is a black-and-white image, execute the second refresh strategy, drive the master control chip to generate a second drive instruction according to the second refresh strategy, drive the display driver chip to convert the control signal of the second drive instruction into a corresponding voltage waveform, drive the electronic paper display screen to refresh the image according to the refresh strategy corresponding to the second drive instruction, and update the displayed image; determine that it is a multi-color image, which is the target image, and input it into the image detection model.

[0018] Step S200: Input the target image into the image segmentation unit of the image detection model to obtain K target segmentation images and image position identifiers, input the K target segmentation images into the hash algorithm detection unit of the image detection model, and obtain hash values ​​of the K target segmentation images through the BMH hash algorithm.

[0019] In the embodiment of the present application, the image difference detection is located at the front end of the entire refresh process. The main control chip first performs a difference detection after acquiring the target image. The detection result directly affects the subsequent generation of drive instructions. The difference detection between the target image and the current image can be efficiently performed to accurately find the part of the image that has actually changed, avoiding subsequent driving and refreshing operations on most of the same areas, thereby directly reducing the overall refresh workload and improving work efficiency. Therefore, improving the efficiency of image difference detection is an efficient, simple and low-cost method for driving the refresh of the image of an electronic paper display screen. Specifically, the target image is divided into K target segmented images, each of which carries an image position identifier, in preparation for accurately locating the position of each segmented image in subsequent image recognition and screen refresh operations. The BMH image hash algorithm is selected to calculate the average color value of each target segmented image. The BMH (BlockMeanHash) image hash algorithm is called "block mean hash" or "block average hash". It is an existing and low-cost image hash technology. It creates a hash by dividing the image into multiple small blocks and then calculating the average color value of each block. The size of the segmented block depends on the hash granularity required by the electronic paper display application scenario; smaller segments provide more refined hashes, while larger segments produce coarser hashes. For each segmented block, the average value of the red, green, and blue (RGB) channels of all pixels in the area is calculated. Each segmented block can be represented by a triple (R, G, B) to represent its average color. When comparing two images, the Hamming distance between the two hashes can be calculated. A smaller distance means that the two images are similar. The hash values ​​of each target segmented image are calculated, and a mapping relationship is established between each hash value and the image position identifier of the corresponding target segmented image. This mapping relationship helps to make difference judgments in subsequent secondary image recognition.

[0020] Furthermore, K target segmentation images and image position identifiers are obtained, including:

[0021] Acquire a sample image, determine the number of pixels of a segmented image of the sample image according to the total number of pixels of the electronic paper display screen and a specific application scenario, calculate the ratio of the total number of pixels of the electronic paper display screen to the number of pixels of the segmented image of the sample image, and obtain the number of segmentations K of the sample image;

[0022] Determine whether K is a perfect square number.

[0023] If so, the sample target image is segmented into The grid,

[0024] If not, select the two closest factors r and c so that r×c=K, and divide the sample image into r×c grids;

[0025] Mark each grid with a position identifier to obtain an image segmentation unit;

[0026] The target image is input into an image segmentation unit to obtain K target segmentation images and K image position identifiers.

[0027] In the embodiment of the present application, an image segmentation unit is constructed, and the number of pixels of each segmented image of the sample target image is determined according to the total number of pixels of the electronic paper display screen and the specific application scenario of the electronic paper display screen. The number of pixels of each segmented image is consistent, and the ratio of the total number of pixels of the electronic paper display screen to the number of pixels of the segmented image of the sample target image is calculated to meet the visual requirement granularity of the electronic paper display screen in the specific application scenario, which is also the hash granularity of the BMH image hash algorithm. Specifically, the resolution of the electronic paper display screen is obtained, and the resolution is the number of pixels on the width and height of the display screen, and the total number of pixels is the product of the width and height of the resolution. Based on the total number of pixels of the electronic paper display and the specific application scenario of the electronic paper display, the number of pixels of the segmented image of the sample target segmented image can be manually determined, and the ratio of the total number of pixels of the electronic paper display to the number of pixels of the segmented image of the sample target image can be calculated to obtain the number of segmentation K of the sample target image; or the sample target images under the same application scenario can be obtained from multiple sources, and 80% of the sample target images are used as the training set. According to the total number of pixels of the electronic paper display and the specific application scenario of the electronic paper display, various numbers of pixels of the segmented image of the sample target image are tried, and each scheme is pre-cut to analyze whether the cutting result meets the user's visual comfort threshold requirements when the image is refreshed according to the segmented image and the refresh efficiency threshold requirements of the specific application scenario. If the cutting result is greater than the visual comfort threshold and less than the refresh efficiency threshold, and meets the two threshold requirements, then the number of pixels of the segmented image of the selected sample target image is reasonable, and the remaining 20% ​​of the sample target images are used as the verification set for the final evaluation of the accuracy of the selected segmentation scheme. The number of segmentation K of the sample target image is obtained, K is an integer greater than 0, and if K is a perfect square number, the sample target image is segmented into If K is not a perfect square number, select the two closest factors r and c so that r×c=K, and divide the sample target image into r×c grids. Label each grid with an image position identifier, and mark the row and column of each grid in the sample target image. This is a key step in the image segmentation process, which is used to distinguish the position of each sample segmented image in the original image and obtain an image segmentation unit. Input the target image into the image segmentation unit to obtain K target segmented images and their corresponding K image position identifiers.

[0028] Step S300: traverse the image position identifier, calculate the Hamming distance between the target segmented image hash value and the current segmented image hash value under each image position identifier, map the Hamming distance to the image position identifier one by one, and pre-check the Hamming distance through a preset first threshold to obtain M pre-check results and N secondary detection results, where M and N are integers ≥ 0 respectively, and M+N=K.

[0029] Specifically, the image position identifiers are traversed, the target segmentation image hash value and the current segmentation image hash value under the same image position identifier are matched, the Hamming distance between the two is calculated, and a one-to-one mapping relationship is established between the calculated Hamming distance and the corresponding image position identifier. The Hamming distance can be used to measure the distance between the two hash values. The calculation is simple and fast. The smaller the Hamming distance is, the more similar the two images are visually.

[0030] Furthermore, before the target image is input into the image segmentation unit of the image detection model, the method includes:

[0031] K segmented images of the image currently displayed on the electronic paper display screen and their corresponding image position identifiers and hash values ​​are extracted from the resident foreground image set, and the image position identifiers of the K current segmented images and their corresponding hash values ​​are input into the hash algorithm detection unit.

[0032] Specifically, K current segmented images of the currently displayed image and their corresponding hash values ​​and image position identifiers are selected from the resident foreground image set, and the hash value and image position identifier corresponding to each current segmented image are input into the hash algorithm detection unit to prepare for identifying the difference between the target image and the currently displayed image. The resident foreground image set can be stored in an external resident card, and the specific interface and connection method between the external resident card and the main control chip can realize data transmission according to the interface protocol.

[0033] Furthermore, the obtained Hamming distance is pre-checked by using a preset first threshold value to obtain M pre-check results and N secondary check results, including:

[0034] The K target segmentation images are input into a hash algorithm detection unit, a hash value of each target segmentation image is obtained by a BMH hash algorithm, and the K target segmentation images with the image position identifiers and their corresponding hash values ​​are stored in a foreground image set;

[0035] Traversing the image position identifiers, calculating the Hamming distance between the target segmented image hash value and the current segmented image hash value under the same image position identifier, and establishing a mapping relationship between the obtained Hamming distance and the corresponding position identifier;

[0036] A first threshold is preset, and the target segmentation images corresponding to the Hamming distance greater than the preset first threshold are added to the first image update list to obtain M preliminary inspection results, and the target segmentation images corresponding to the Hamming distance less than the preset first threshold are N secondary inspection results.

[0037] In an embodiment of the present application, the hash detection method can quickly identify the difference in images. It is determined that the hash value of each target segmented image is calculated using the BHM hash algorithm. The calculated hash value of each target segmented image can be input into the hash value list, and the Hamming distance between the hash value of the target segmented image and the current segmented image under the same image position identifier is calculated and input into the hash value list. A first threshold is preset, and the K obtained Hamming distances are compared with the first threshold to obtain M pre-inspection results with a Hamming distance greater than the first threshold, and N results to be detected with a Hamming distance less than the first threshold, which are the results to be tested. These N results to be tested may be due to the limitations of the BMH hash detection method, or due to hash conflicts, and the images are judged to be similar and do not need to be updated. Specifically, since the multi-color display of the electronic paper display screen has high requirements on the color depth and brightness of the image, and the pre-check is to detect the differences between K paired segmented images, the pre-check detection method needs to be sensitive to local color changes and details, and also sensitive to the edge and detail changes of the image. It is determined that the BMH hash algorithm is sensitive to the overall brightness and color distribution changes of the image, simple to calculate, fast, and suitable for segmenting images, but is not sensitive to local detail changes and cannot capture local color changes and details well. The BMH hash algorithm is embedded in the hash detection unit, the hash value of each target segmented image is calculated, and the K target segmented images with image position identifiers and their corresponding hash values ​​are stored in the foreground image set for subsequent new image difference detection. The K current segmented images of the current display image and the K target segmented images of the target image in the foreground image set are all segmented by the image segmentation unit into K target segmented images with image position identifiers and K current segmented images with image position identifiers. The same image position identifier indicates that the target segmented image and the current segmented image have the same position in the original image. Traverse the image position identifiers, match the hash values ​​of the target segmented image and the current segmented image corresponding to the same image position identifier, calculate the Hamming distance between the hash value of each target segmented image and the hash value of the corresponding current segmented image, obtain the Hamming distance of the paired segmented images under each image position identifier, and establish a mapping relationship between the obtained Hamming distance and the corresponding image position identifier. Perform a pre-check, preset a first threshold, compare K Hamming distances with the first threshold, obtain M Hamming distances greater than the first threshold, and according to the image position identifiers corresponding to the M Hamming distances, find the target segmented image under the same image position identifier from the K target segmented images, add the M target segmented images to the first list of image updates, and obtain M pre-check results. The M pre-check results include M target segmented images and their image position identifiers. These target segmented images can be quickly identified as different from the current segmented images through BMH hash detection, and are images that must be updated.The remaining N target segmentation images corresponding to the Hamming distances less than the first threshold may not cause the correct judgment of the visual difference due to the limitations of the BMH hash detection method or hash conflicts. These N target segmentation images need to be recognized again.

[0038] Step S400: define the N image position identifiers of the results to be secondary detected as secondary detection position identifiers, arrange the secondary detection position identifiers in ascending order according to their corresponding Hamming distances to obtain a pre-detection sequence, and combine the current segmented image under the secondary detection position identifier to form a paired segmented image with the results to be secondary inspected to obtain a secondary recognition image set.

[0039] In an embodiment of the present application, the N results to be re-detected include N target segmentation images whose Hamming distance is less than a first threshold and their corresponding image position identifiers. Specifically, the target image is pre-detected by the image detection model to obtain N target segmentation images that need to be re-identified, and the image position identifiers corresponding to the N target segmentation images that need to be re-identified are defined as secondary detection position identifiers. The secondary detection position identifiers are arranged in ascending order of the corresponding Hamming distances to form a pre-detection detection sequence, and the secondary detection position identifiers are traversed. For each secondary detection position identifier, there is a corresponding paired segmentation image, including the target segmentation image and the current segmentation image. The paired segmentation images under the N secondary inspection position identifiers are grouped together to construct a secondary recognition image set.

[0040] Step S500: performing difference detection on each pair of segmented images in the secondary recognition image set by using a histogram method, a structural similarity index and a feature point matching method respectively, arranging the secondary detection position identifiers in ascending order according to their corresponding detection results, and obtaining a first detection sequence, a second detection sequence and a third detection sequence respectively.

[0041] In the embodiment of the present application, visual detection technologies are traversed to screen out visual detection technologies suitable for detecting static image differences and capable of making up for the shortcomings of BMH hash detection, analyze the reasons for the errors in BMH hash detection, and determine the histogram method, structural similarity index and feature point matching method for image difference recognition of paired segmented images in the secondary recognition image set. Specifically, the BMH hash detection method may have misjudgments, such as hash conflicts, or be insensitive to changes in local details, such as fine-tuning of image color but the light and dark relationship and structure remain unchanged, or insensitive to changes in image brightness and contrast. The histogram method directly focuses on the actual pixel value distribution characteristics of the image (such as the distribution of grayscale values ​​or color values), and can detect segmented images that are misjudged due to hash conflicts; the histogram method is more sensitive to changes in image color. Even if the light and dark relationship and structure of the image remain unchanged, as long as the color is fine-tuned, the histogram will be reflected, and the hash detection method can detect segmented images that are misjudged due to fine-tuning of image color but the light and dark relationship and structure remain unchanged. The secondary recognition image set is traversed, and the histogram method is used to perform difference recognition on the paired segmented images. It can detect misjudgments caused by hash conflicts or slight adjustments to the image color but the light and dark relationship and structure remain unchanged. The histogram detection method is used to detect the secondary recognition image set, and a mapping relationship is established between the calculated histogram distance and the corresponding secondary detection position identifier, and the secondary detection position identifier is arranged in ascending order according to the histogram method detection result to obtain the first detection sequence. The structural similarity index has a good detection ability for changes in image structure, and can detect segmented images misjudged due to hash conflicts, and can make up for some insensitive areas detected by the hash algorithm and histogram method. For example, the structural similarity index is very sensitive to changes in local details, and can identify differences in the boundaries and local details of segmented images, and can identify brightness differences between different areas of the image. The secondary recognition image set is traversed, and the structural similarity index is used to perform difference recognition on the paired segmented images. It can detect misjudgments caused by hash conflicts, hash detection methods, and histogram detection methods. The structural similarity index method detects the secondary recognition image set, converts the calculated structural similarity index into a difference metric, establishes a mapping relationship between the converted structural similarity index and its corresponding secondary detection position identifier, and arranges the secondary detection position identifiers in ascending order of the converted structural similarity index to obtain a second detection sequence. The feature point matching method focuses on the feature points (such as corner points, edge points, etc.) in the image and can detect segmented images misjudged due to hash conflicts and misjudgments caused by the insensitivity of the histogram method and the structural similarity index method. Compared with the structural similarity index, it pays more attention to the feature points in the image, and the local and detail detection granularity is refined. The feature point matching method detects the secondary recognition image set, establishes a mapping relationship between the calculated feature point matching value and its corresponding secondary detection position identifier, and arranges the secondary detection position identifiers in ascending order of the feature point matching value to obtain a third detection sequence.Through the diversified detection of local and detailed aspects by the above three detection methods, the combination of the three methods can largely avoid missed detections. Because each method has its advantages and limitations, using one method alone may miss certain types of changes. When the three methods are combined, the changes in the image can be comprehensively detected from the three aspects of pixel value distribution, structure and feature points, thereby reducing the possibility of missed detection. The larger the detection data of the three visual detection methods, the greater the image difference.

[0042] Further, the first detection sequence, the second detection sequence and the third detection sequence are obtained respectively, including:

[0043] Based on the secondary recognition image set, the histogram method is used to perform difference detection on each pair of segmented images in the secondary recognition image set, a mapping relationship is established between the obtained histogram distance and the secondary detection position identifier, and the secondary detection position identifiers are arranged in ascending order according to their corresponding histogram distances to obtain a first detection sequence;

[0044] Based on the secondary recognition image set, the structural similarity index method is used to perform difference detection on each pair of segmented images in the secondary recognition image set, and the obtained structural similarity index is converted into a difference metric, and the range of the converted structural similarity index is [0, 2]. A mapping relationship is established between the converted structural similarity index and the secondary detection position identifier, and the secondary detection position identifiers are arranged in ascending order according to their corresponding converted structural similarity indexes to obtain a second detection sequence;

[0045] Based on the secondary recognition image set, ORB in the feature point matching method is used to perform difference detection on each pair of segmented images in the secondary recognition image set, a mapping relationship is established between the obtained ORB difference degree and the secondary detection position identifier, and the secondary detection position identifiers are arranged in ascending order according to their corresponding ORB difference degrees to obtain a third detection sequence.

[0046] Specifically, the histogram method is used to detect the difference between paired segmented images based on the secondary recognition image set, and the distribution of pixel values ​​in the image is statistically analyzed to characterize the characteristics of the image. For paired segmented images, the degree of difference between the images can be detected by comparing their histograms. The histogram method can capture more information inside the image by statistically analyzing the distribution of pixel values, thereby making up for the defect of the BMH hash algorithm in insufficient utilization of image details and internal structure information to a certain extent. The histogram distance reflects the degree of difference between paired images. The smaller the distance, the more similar the images are in terms of features. When calculating the histogram distance, the distance metric selected in this embodiment is the Bhattacharyya distance, and the formula is:

[0047]

[0048] Among them, H1 and H2 are the histograms of the target segmentation image and the current segmentation image, respectively. H1(i) and H2(i) respectively represent the intervals of histograms H1 and H2 in the i-th histogram statistics, and n represents the number of segmented images.

[0049] The structural similarity index (SSIM) is an indicator used to evaluate the visual difference between two images, which takes into account the brightness, contrast and structural information of the image. In the recognition of paired segmented images, when there are structural changes, local detail changes or contrast changes in the images, the BMH hash algorithm and the histogram method may not be able to accurately identify the similarity of the images. SSIM can more accurately measure the similarity between images, thereby making up for the shortcomings of the BMH hash algorithm and the histogram method in these aspects. The calculation formula of SSIM is as follows:

[0050]

[0051] C1=(K1L) 2

[0052] C2=(K2L) 2

[0053] Among them, x and y are the target segmentation image and the current segmentation image, μ x and μ y are the average values ​​of the target segmentation image and the current segmentation image, σ x and σ y are the standard deviations of the target segmentation image and the current segmentation image, σ xy is the covariance of x and y, C1 and C2 are small constants used to avoid the denominator being zero, K1 and K2 are small constants, and L is the maximum pixel value of the segmented image. The SSIM value range is [-1, 1]. When the SSIM value is closer to 1, it means that the structural similarity of the two images is higher. In order to facilitate subsequent image recognition, y=1-x, y∈[0, 2] is converted through the difference metric. The larger the SSIM value parameter value after the difference metric conversion, the greater the difference between the paired images, forming the second detection sequence.

[0054] ORB (Oriented FAST and Rotated BRIEF) is a method in feature point matching. It combines the advantages of FAST key point detector (Oriented FAST) and BRIEF descriptor (Rotated BRIEF). It is particularly suitable for image matching application scenarios that require fast processing. Some literature and tutorials refer to ORB as "oriented FAST corner point detection and rotated BRIEF descriptor algorithm" or "oriented FAST feature point detection and rotated BRIEF descriptor algorithm". When the ORB algorithm is used to determine the degree of difference between paired images, the main steps include feature point extraction, feature descriptor generation, and feature matching. First, the FAST (Features from Accelerated Segment Test) algorithm is used to detect key points in the image, and possible key points are identified by performing a fast intensity test on the pixels in the image. For each detected key point, ORB uses the BRIEF (Binary Robust Independent Elementary Features) algorithm for feature description. BRIEF generates binary descriptors and determines the binary code by comparing the brightness of the pixel pairs around the key point. The Hamming distance is used to measure the difference between two feature descriptors. The larger the Hamming distance, the greater the difference between the two feature descriptors.

[0055] In summary, the BMH hash algorithm is a relatively simple image difference measurement method. The histogram method has a certain degree of image difference detection granularity refinement compared to the BMH hash algorithm. The histogram method generates one or more color histograms by statistically analyzing the pixel value distribution of each color channel (such as the red, green, and blue channels in the RGB space), reflecting the color composition and hue distribution of the segmented image in each color channel, thereby providing richer information. It not only retains the color information of the original image, but also can better reflect the color features and visual effects in the image, making the image description more accurate and comprehensive. Compared with the histogram method, the histogram method only describes the distribution of color intensity, while SSIM begins to focus on the structural information of the image, not just the distribution of pixel values. It measures the difference from the perspective of the physical structure of the image, considering multiple aspects such as brightness, contrast, and structure, and has a deeper analysis of the image. Compared with SSIM, ORB focuses on the comparison of the overall structure, while ORB goes deep into the local feature points and local feature description of the image, and can capture more subtle local changes, developing from the difference measurement of the overall structure to the accurate capture and description of local features. From the BMH hash algorithm to the histogram method, to SSIM, and finally to ORB image difference detection, each step adds new dimensions and depth based on the previous one, making image analysis and matching more and more sophisticated and accurate.

[0056] Step S600: Taking the pre-check detection sequence as a reference, traverse the secondary detection position identifier, calculate the total number of steps of its ranking improvement in the first detection sequence, and obtain a first difference score; taking the first detection sequence as a reference, traverse the secondary detection position identifier, calculate the total number of steps of its ranking improvement in the second detection sequence, and obtain a second difference score; taking the second detection sequence as a reference, traverse the secondary detection position identifier, calculate the total number of steps of its ranking improvement in the third detection sequence, and obtain a third difference score.

[0057] Furthermore, the first difference score, the second difference score and the third difference score include:

[0058] Determine that the number of parameters in the pre-detection detection sequence, the first detection sequence, the second detection sequence, and the third detection sequence is N, and assign a constraint coefficient w=1 / N to each detection sequence, where N is the number of results to be re-detected;

[0059] Taking the pre-check detection sequence as a reference, traverse the secondary detection position identifier, identify that its ranking in the first detection sequence is higher than its ranking in the pre-check detection sequence, calculate the total number of steps for adjusting from a low ranking to a high ranking, combine the obtained total number of steps with the constraint coefficient, and obtain a first difference score;

[0060] Taking the first detection sequence as a reference, traverse the secondary detection position identifier, identify that its ranking in the second detection sequence is higher than its ranking in the first detection sequence, calculate the total number of steps from the low ranking to the high ranking, combine the obtained total number of steps with the constraint coefficient, and obtain a second difference score;

[0061] Taking the second detection sequence as a benchmark, traverse the secondary detection position identifier, identify that its ranking in the third detection sequence is higher than its ranking in the second detection sequence, calculate the total number of steps from the low ranking to the high ranking, combine the obtained total number of steps with the constraint coefficient, and obtain a third difference score.

[0062] In the embodiment of the present application, the three levels of difference scores are obtained by four different visual detection technologies: hash value, histogram method, SSIM index and ORB feature point. Each technology focuses on different image characteristics, such as overall similarity, color distribution, structural information and local features, etc., thereby providing a comprehensive evaluation of image differences. The calculation process from the first difference score to the third difference score is progressive, and the difference is quantified by calculating the number of steps of parameter sorting adjustment, which not only reflects the degree of difference between images, but also provides an intuitive way to measure the magnitude of change, which helps to quickly locate paired segmented images with large image differences. The three levels of difference scores constitute a systematic evaluation framework, so that different types of paired segmented images are compared on the same scale, which provides a guarantee for subsequent comprehensive data analysis and refresh strategy formulation. Specifically, the number of parameters in the pre-detection detection sequence, the first detection sequence, the second detection sequence and the third detection sequence is first determined to be N, and the number of parameters in each detection sequence is consistent with the number of secondary detection results. The number of results to be tested again is affected by factors such as the diversity of the content of the target image and the currently displayed image. It is impossible to ensure that the number of results to be tested again obtained by the pre-test is consistent each time the image is refreshed. The number of parameters in the pre-test sequence and the subsequent multi-dimensional test sequence is related to the number of results to be tested again, resulting in a lack of comparability in the difference scores under different batches of image refreshes. It is difficult to use a unified standard to reflect the difference in images in the future. For example, when the current image is refreshed, there are 5 parameters in ascending order in each test sequence; and when the previous image is refreshed, there are 7 parameters in ascending order in each test sequence. When calculating the number of steps for adjusting the parameters from low ranking to high ranking, the number of steps for adjusting the parameters from the lowest ranking to the highest ranking is 4 under the current image refresh; the number of steps is 6 under the previous image refresh. It can be seen that the number of parameters affects the difference score. In order to ensure that the subsequent difference comprehensive score and threshold can accurately reflect the image difference, a constraint coefficient is imposed on the total number of steps obtained by comparing the pre-detection detection sequence with the first detection sequence, a constraint coefficient is imposed on the total number of steps obtained by comparing the first detection sequence with the second detection sequence, and a constraint coefficient is imposed on the total number of steps obtained by comparing the second detection sequence with the third detection sequence, S'=S×1 / N, where S' represents the difference score, S represents the total number of steps, and 1 / N is the constraint coefficient. Imposing a constraint coefficient can eliminate the influence of the number of parameters on the multi-level difference score, making the multi-level difference score system more adaptable. No matter how the external factors change, the consistency and rationality of the score can be maintained as much as possible, and a stable image difference evaluation mechanism can be established.

[0063] Step S700: Synchronize the first difference score, the second difference score and the third difference score to the difference analysis model to obtain the difference analysis value of the secondary recognition image set, wherein the difference analysis model is based on a multivariate regression model, with three difference scores as input and the difference analysis value as output.

[0064] Furthermore, the difference analysis model includes:

[0065] Difference analysis model, including:

[0066] Obtain sample images from multiple sources, randomly form sample paired images in pairs, input the sample images into the image detection model, and obtain a sample secondary recognition image set after pre-checking;

[0067] Obtaining a sample first difference score, a sample second difference score, and a sample third difference score of the sample paired segmented images in the sample secondary recognition image set, as well as a sample actual difference value of the sample secondary recognition image set, wherein the sample actual difference value is obtained by manual annotation;

[0068] The multivariate regression model is used as the framework, the sample first difference score, the sample second difference score and the sample third difference score are used as input items, and the sample difference analysis value of the sample secondary recognition image set is used as the output to construct a difference analysis model, wherein the multivariate regression model is as follows:

[0069]

[0070] in, is the sample difference analysis value of the sample secondary recognition image set, β0 is the intercept term, β1, β2, β3 are the sample regression coefficients corresponding to the first, second, and third difference scores of the sample, respectively, and ε is the error term;

[0071] The optimization is performed in the sample multidimensional coefficient space so that the sum of square errors between the sample difference analysis value of the sample secondary recognition image set output by the multivariate regression model and the sample actual difference value is minimized. The multivariate regression model obtained by the optimization is a difference analysis model, wherein the sample multidimensional coefficients include β0, β1, β2 and β3, and the formula for the sum of square errors is as follows:

[0072]

[0073] Among them, S is With y i The sum of squared errors between them, n is the number of sample paired segmentation images, y i is the actual sample difference value of the i-th sample pairwise segmented image, It is the sample difference analysis value of the i-th sample paired segmentation image.

[0074] In the embodiment of the present application, the generalization ability and accuracy of image difference judgment are improved by constructing a difference analysis model. Specifically, sample images are obtained from multiple sources, ranging from highly similar to obviously different, including natural images, text images, and graphic images, and these images are subjected to dithering, ranging from black and white to six colors. The diversity and degree of variation of the sample images ensure that the model can be trained and tested in a wide range of situations, improving its generalization ability and accuracy. Randomly form sample paired images in pairs, and one of the sample paired images is selected as the sample target image. The sample paired images are pre-checked to obtain N results of the sample paired images to be recognized twice. Based on the N results of the sample paired images to be recognized twice, a sample pre-check detection sequence and a sample secondary recognition image set are constructed, and the sample paired segmented images in the sample secondary recognition image set are subjected to diversified visual inspections of the histogram method, the structural similarity index, and the feature point matching method to obtain the sample first detection sequence, the sample second detection sequence, and the sample third detection sequence, and a difference analysis is performed to obtain the sample first difference score, the sample second difference score, and the sample third difference score. The actual difference values ​​of N sample paired segmented images in the sample secondary recognition image set are obtained through the manual annotation method. The actual sample difference values ​​of N sample paired segmented images are summed to obtain the actual sample difference value of the sample secondary recognition image set. The manual annotation method needs to determine the scoring dimension for evaluating the difference between sample segmented images. Experts or trained annotation personnel can be selected to annotate through special annotation tools, such as color, texture, shape and content dimensional differences, establish corresponding difference scoring rules, select a suitable scoring scale for each dimension, which can be a continuous value or a discrete level, introduce a weight mechanism, and obtain the actual sample difference value of each sample paired segmented image in the sample secondary recognition image set. Then construct a multivariate regression model as follows:

[0075]

[0076] in, is the sample difference analysis value of the sample secondary recognition image set, β0 is the intercept term, β 1、 β 2、 β3 are the sample regression coefficients corresponding to the first, second and third sample difference scores, and ε is the error term. The multivariate regression model is trained using the sample paired segmentation images of the sample images. The sample regression coefficients β0, β 1、 The optimal sample multidimensional coefficient space of β2 and β3 is searched, so that the sample difference analysis value of the sample secondary recognition image set output by the model is The sum of squared errors between the actual difference value y of the sample in the sample secondary recognition image set is the smallest, that is, the sum of squared vertical distances is the smallest. The sum of squared errors is as follows:

[0077]

[0078] Among them, S is With y i The sum of squared errors between them, n is the number of sample paired segmentation images, y i is the actual sample difference value of the i-th sample pairwise segmented image, is the sample difference analysis value of the i-th sample paired segmentation image. 80% of the sample paired segmentation images are used for the training set and 20% for the validation set. The sample regression coefficient is estimated using the least squares method on the training set. The sample regression coefficient includes β0, β 1、 β2 and β3, the sample difference analysis value of the sample secondary recognition image set The sum of squared errors between the actual difference value y and the sample is minimized, and the least squares method is used on the validation set to find the optimal sample regression coefficients β0, β 1、 β 2、 β3, the sample difference analysis value of the sample secondary recognition image set The sum of squared errors between the actual difference value y of the sample is minimized to verify the model performance, converge the model, and obtain the difference analysis model.

[0079] S800: Determine if the difference analysis value is greater than a preset second threshold, remove duplicate images, and obtain P secondary detection results, where P≤N.

[0080] P second detection results are obtained, including:

[0081] Obtaining a difference analysis value of the secondary recognition image set;

[0082] If it is determined that the difference analysis value of the secondary recognition image set is greater than a preset second threshold, the target segmentation images corresponding to the secondary detection position identifiers that are adjusted from low ranking to high ranking in the first inspection sequence, the second inspection sequence, and the third inspection sequence during the three difference scoring processes are extracted, duplicate images are eliminated, and the retained target segmentation images are added to the second image update list to obtain P second detection results.

[0083] Specifically, a second threshold is preset. When the difference analysis value of the secondary recognition image set is greater than the preset second threshold, it means that the N paired segmented images in the secondary recognition image set have a high degree of difference as a whole. Extract the target segmented images corresponding to the secondary detection position marks adjusted from low ranking to high ranking in the first inspection sequence, the second inspection sequence, and the third inspection sequence. There may be some repeated images in the extracted target segmented images. Eliminating these repeated images can avoid redundant information. Add the retained target segmented images to the second image update list to obtain P second detection results. The second detection results include P target segmented images and their image position marks, indicating that after multivariate visual detection, P target images with update value are screened out from the N paired segmented images in the secondary recognition image set, P≤N.

[0084] Step S900: Determine whether the result of M+P is less than a preset third threshold.

[0085] If yes, the master control chip is driven to generate a local refresh drive instruction, the display driver chip is driven to convert the control signal of the instruction into a corresponding voltage waveform, and the electronic paper display screen is driven to perform a local image refresh according to the voltage waveform corresponding to the instruction to display the target image;

[0086] If not, the driver control chip generates a global refresh drive instruction, drives the display driver chip to convert the control signal of the instruction into a corresponding voltage waveform, drives the electronic paper display screen to perform global image refresh according to the voltage waveform corresponding to the instruction, and displays the target image.

[0087] In this embodiment, a third threshold is preset, and the third threshold is the number K of target segmented images obtained by the image segmentation unit of the target image. The entire method for driving the image refresh of the electronic display device is to determine different refresh strategies to drive the refresh based on the comparison between the result of M+P and the third threshold. It is judged whether the result of M+P is less than the third threshold. If so, the current state is suitable for adopting the local refresh strategy, and the driving master control chip generates a first driving instruction, indicating that it is detected that the current image-related state is in a state suitable for local processing relative to the segmentation of the target image, and the driving display driver chip converts the control signal of the first driving instruction into a corresponding voltage waveform, which is customized according to the local refresh strategy and only affects the area on the electronic paper display screen that needs to be locally updated. The second list image and its position identifier are locally updated according to the first update list and image update. The corresponding position of the current display image. If not, the current state is suitable for adopting the global refresh strategy, and the driving master control chip generates a second driving instruction, indicating that it is detected that the current image-related state needs to be comprehensively and integrally processed relative to the segmentation of the target image, and the display driver chip converts the control signal of the second driving instruction into a corresponding voltage waveform, which is designed for the global refresh strategy, and drives the electronic paper display screen to refresh the image according to the global refresh strategy corresponding to the second driving instruction.

[0088] In summary, the method for driving an electronic display device to refresh an image provided by the embodiment of the present application has the following technical effects:

[0089] 1. Determine whether the image to be displayed is a non-black and white image, and obtain the target image, which can avoid unnecessary image difference judgment, shunt the execution of the refresh method of the image of the driving electronic display device, improve the overall refresh efficiency, input the target image into the image detection model, obtain K target segmentation images, perform pre-inspection, obtain M pre-inspection results and N secondary detection results, quickly identify the target segmentation image that needs to be subjected to multivariate visual detection, improve the accuracy of image detection, reduce the amount of calculation of the system, and improve the overall refresh efficiency;

[0090] 2. Obtaining the first detection sequence, the second detection sequence and the third detection sequence can more comprehensively capture the differences between the paired segmented images and enhance the comprehensiveness of the detection;

[0091] 3. Obtaining the first difference score, the second difference score and the third difference score reflects the degree of difference between the paired segmented images under different visual detection technologies, which helps to comprehensively evaluate the overall difference between the paired segmented images in the secondary recognition image set;

[0092] 4. Through the difference analysis model, the first difference score, the second difference score and the third difference score are comprehensively judged by multivariate regression, and the scattered difference scores are combined to obtain the difference analysis value of the secondary recognition image set, which improves the judgment accuracy of the paired segmented images in the secondary recognition image set;

[0093] 5. The difference analysis value obtained by the difference analysis model is greater than the preset second threshold value, and P second detection results are obtained. It is judged whether the result of M+P is less than the third threshold value. The master control chip is driven to generate corresponding drive instructions through the judgment result, and the display drive chip is driven to convert the control signal of the corresponding drive instruction into a corresponding voltage waveform, and the electronic paper display is driven to refresh the image according to the waveform corresponding to the corresponding drive instruction, update the displayed image, minimize unnecessary refresh operations, reduce energy consumption, improve the overall refresh efficiency, and enhance the user experience.

[0094] In one embodiment, a system for driving an image refresh of an electronic display device is provided, wherein the internal structure Figure 2 As shown. The drive refresh system includes a main control chip module, a display driver chip module and a storage chip module, and the main control chip module, the display driver chip module and the storage chip module are electrically connected through a communication line, wherein the storage chip module of the drive refresh system is externally connected to the main control chip module, and is used to store the foreground atlas, receive the picture from the main control chip and assist the main control chip to obtain the current display image in the foreground atlas; the main control chip module of the drive refresh system is used to receive the current display image stored in the storage chip module, receive the image to be displayed, and determine the difference area by comparing the target image with the current display image to generate a corresponding drive instruction; the display driver chip module of the drive refresh system converts the control signal of the corresponding drive instruction into a corresponding voltage waveform, and drives the corresponding area of ​​the electronic paper display screen to refresh according to the corresponding voltage waveform. The drive refresh system executes a method for refreshing the image of a driving electronic display device.

[0095] Those skilled in the art will understand that Figure 2 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0096] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. 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 application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for driving an image refresh of an electronic display device, characterized in that: The electronic display device includes an electronic paper display screen, and the method includes: Acquire an image to be displayed, determine whether the image to be displayed is a non-black and white image, and obtain a target image, wherein the image to be displayed is a static image formed by a combination of text and / or pictures; Input the target image into the image segmentation unit of the image detection model to obtain K target segmentation images and image position identifiers, input the K target segmentation images into the hash algorithm detection unit of the image detection model, and obtain hash values ​​of the K target segmentation images through the BMH hash algorithm; Traversing the image position identifiers, calculating the Hamming distance between the target segmented image hash value and the current segmented image hash value under each image position identifier, mapping the Hamming distance to the image position identifier one by one, pre-checking the Hamming distance by a preset first threshold, and obtaining M pre-check results and N secondary check results, wherein M and N are integers ≥ 0 respectively, and M + N = K; The image position identifiers of the N results to be secondary detected are defined as secondary detection position identifiers, the secondary detection position identifiers are arranged in ascending order according to their corresponding Hamming distances to obtain a pre-detection sequence, and the current segmented image under the secondary detection position identifier is combined with the result to be secondary detected to form a paired segmented image to obtain a secondary recognition image set; Performing difference detection on each pair of segmented images in the secondary recognition image set by using a histogram method, a structural similarity index and a feature point matching method respectively, arranging the secondary detection position identifiers in ascending order according to their corresponding detection results, and obtaining a first detection sequence, a second detection sequence and a third detection sequence respectively; Taking the pre-check detection sequence as a reference, traverse the secondary detection position identifier, calculate the total number of steps of its ranking improvement in the first detection sequence, and obtain a first difference score; taking the first detection sequence as a reference, traverse the secondary detection position identifier, calculate the total number of steps of its ranking improvement in the second detection sequence, and obtain a second difference score; taking the second detection sequence as a reference, traverse the secondary detection position identifier, calculate the total number of steps of its ranking improvement in the third detection sequence, and obtain a third difference score; Synchronizing the first difference score, the second difference score and the third difference score to a difference analysis model to obtain a difference analysis value of the secondary recognition image set, wherein the difference analysis model is based on a multivariate regression model, takes the three difference scores as inputs, and takes the difference analysis value as output; Determine that the difference analysis value is greater than a preset second threshold, remove duplicate images, and obtain P secondary detection results, where P≤N; Determine whether the result of M+P is less than a preset third threshold, If yes, the master control chip is driven to generate a local refresh drive instruction, the display driver chip is driven to convert the control signal of the instruction into a corresponding voltage waveform, and the electronic paper display screen is driven to perform a local image refresh according to the voltage waveform corresponding to the instruction to display the target image; If not, the driver control chip generates a global refresh drive instruction, drives the display driver chip to convert the control signal of the instruction into a corresponding voltage waveform, drives the electronic paper display screen to perform global image refresh according to the voltage waveform corresponding to the instruction, and displays the target image.

2. The method for refreshing an image of a driving electronic display device as claimed in claim 1, characterized in that: Obtain K target segmentation images and image location identifiers, including: Acquire a sample image, determine the number of pixels of a segmented image of the sample image according to the total number of pixels of the electronic paper display screen and a specific application scenario, calculate the ratio of the total number of pixels of the electronic paper display screen to the number of pixels of the segmented image of the sample image, and obtain the number of segmentations K of the sample image; Determine whether K is a perfect square number. If so, the sample target image is segmented into The grid, If not, select the two closest factors r and c so that r×c=K, and divide the sample image into r×c grids; Mark each grid with a position identifier to obtain an image segmentation unit; The target image is input into an image segmentation unit to obtain K target segmentation images and K image position identifiers.

3. The method for refreshing an image of a driving electronic display device as claimed in claim 1, characterized in that: Before inputting the target image into the image segmentation unit of the image detection model, it includes: K segmented images of the image currently displayed on the electronic paper display screen and their corresponding image position identifiers and hash values ​​are extracted from the resident foreground image set, and the image position identifiers of the K current segmented images and their corresponding hash values ​​are input into the hash algorithm detection unit.

4. The method for refreshing an image of a driving electronic display device as claimed in claim 3, characterized in that: The Hamming distance is pre-checked by using a preset first threshold, and M pre-check results and N secondary check results are obtained, including: The K target segmentation images are input into a hash algorithm detection unit, a hash value of each target segmentation image is obtained by a BMH hash algorithm, and the K target segmentation images with the image position identifiers and their corresponding hash values ​​are stored in a foreground image set; Traversing the image position identifiers, calculating the Hamming distance between the target segmented image hash value and the current segmented image hash value under the same image position identifier, and establishing a mapping relationship between the obtained Hamming distance and the corresponding position identifier; A first threshold is preset, and the target segmentation images corresponding to the Hamming distance greater than the preset first threshold are added to the first image update list to obtain M preliminary inspection results, and the target segmentation images corresponding to the Hamming distance less than the preset first threshold are N secondary inspection results.

5. The method for refreshing an image of a driving electronic display device as claimed in claim 1, characterized in that: The first detection sequence, the second detection sequence and the third detection sequence are obtained respectively, including: Based on the secondary recognition image set, the histogram method is used to perform difference detection on each pair of segmented images in the secondary recognition image set, a mapping relationship is established between the obtained histogram distance and the secondary detection position identifier, and the secondary detection position identifiers are arranged in ascending order according to their corresponding histogram distances to obtain a first detection sequence; Based on the secondary recognition image set, the structural similarity index method is used to perform difference detection on each pair of segmented images in the secondary recognition image set, and the obtained structural similarity index is converted into a difference metric, and the range of the converted structural similarity index is [0, 2]. A mapping relationship is established between the converted structural similarity index and the secondary detection position identifier, and the secondary detection position identifiers are arranged in ascending order according to their corresponding converted structural similarity indexes to obtain a second detection sequence; Based on the secondary recognition image set, ORB in the feature point matching method is used to perform difference detection on each pair of segmented images in the secondary recognition image set, a mapping relationship is established between the obtained ORB difference degree and the secondary detection position identifier, and the secondary detection position identifiers are arranged in ascending order according to their corresponding ORB difference degrees to obtain a third detection sequence.

6. The method for driving an image refresh of an electronic display device as claimed in claim 1, characterized in that: The first difference score, the second difference score and the third difference score include: Determine that the number of parameters in the pre-detection detection sequence, the first detection sequence, the second detection sequence, and the third detection sequence is N, and assign a constraint coefficient w=1 / N to each detection sequence, where N is the number of results to be re-detected; Taking the pre-check detection sequence as a reference, traverse the secondary detection position identifier, identify that its ranking in the first detection sequence is higher than its ranking in the pre-check detection sequence, calculate the total number of steps for adjusting from a low ranking to a high ranking, combine the obtained total number of steps with the constraint coefficient, and obtain a first difference score; Taking the first detection sequence as a reference, traverse the secondary detection position identifier, identify that its ranking in the second detection sequence is higher than its ranking in the first detection sequence, calculate the total number of steps from the low ranking to the high ranking, combine the obtained total number of steps with the constraint coefficient, and obtain a second difference score; Taking the second detection sequence as a benchmark, traverse the secondary detection position identifier, identify that its ranking in the third detection sequence is higher than its ranking in the second detection sequence, calculate the total number of steps from the low ranking to the high ranking, combine the obtained total number of steps with the constraint coefficient, and obtain a third difference score.

7. The method for driving an image refresh of an electronic display device as claimed in claim 1, characterized in that: Difference analysis model, including: Obtain sample images from multiple sources, randomly form sample paired images in pairs, input the sample images into the image detection model, and obtain a sample secondary recognition image set after pre-checking; Obtaining a sample first difference score, a sample second difference score, and a sample third difference score of the sample paired segmented images in the sample secondary recognition image set, as well as a sample actual difference value of the sample secondary recognition image set, wherein the sample actual difference value is obtained by manual annotation; The multivariate regression model is used as the framework, the sample first difference score, the sample second difference score and the sample third difference score are used as input items, and the sample difference analysis value of the sample secondary recognition image set is used as the output to construct a difference analysis model, wherein the multivariate regression model is as follows: in, is the sample difference analysis value of the sample secondary recognition image set, β0 is the intercept term, β1, β2, β3 are the sample regression coefficients corresponding to the first, second, and third difference scores of the sample, respectively, and ε is the error term; The optimization is performed in the sample multidimensional coefficient space so that the sum of square errors between the sample difference analysis value of the sample secondary recognition image set output by the multivariate regression model and the sample actual difference value is minimized. The multivariate regression model obtained by the optimization is a difference analysis model, wherein the sample multidimensional coefficients include β0, β1, β2 and β3, and the formula for the sum of square errors is as follows: Among them, S is With y i The sum of squared errors between them, n is the number of sample paired segmentation images, y i is the actual sample difference value of the i-th sample pairwise segmented image, It is the sample difference analysis value of the i-th sample paired segmentation image.

8. The method for refreshing an image of a driving electronic display device as claimed in claim 1, characterized in that: P second detection results are obtained, including: Obtaining a difference analysis value of the secondary recognition image set; If it is determined that the difference analysis value of the secondary recognition image set is greater than a preset second threshold, the target segmentation images corresponding to the secondary detection position identifiers that are adjusted from low ranking to high ranking in the first inspection sequence, the second inspection sequence, and the third inspection sequence during the three difference scoring processes are extracted, duplicate images are eliminated, and the retained target segmentation images are added to the second image update list to obtain P second detection results.

Images