Method, device and readable storage medium for enhancing image recognizability

Abstract

The present application relates to a method, device and readable storage medium for enhancing image recognizability, wherein the method for enhancing image recognizability increases the contrast of the entire image by performing global histogram equalization on the image. By dividing the image into multiple comparison areas, two adjacent comparison areas with high similarity are merged to achieve distinction and recognition of local details of the image. The present application enhances the image from the overall image and the local details of the image, greatly increases the recognition rate of image features, and can effectively identify objects in the image and the environment in which the objects are located.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to a method, device and readable storage medium for enhancing image recognizability. Background Art

[0002] Sales personnel in the consumer goods industry need to visit stores regularly. In addition to selling goods, they also need to perform operations such as tallying in stores. In order to supervise sales personnel to visit stores as required, companies often require sales personnel to take photos of storefronts when visiting stores to verify the authenticity of the visit. At the same time, in order to supervise sales personnel to tally as required, companies will also require sales personnel to take photos of the store environment, including tally shelves, corner warehouses and other locations, to prove that the tally results meet the company's requirements. However, due to the dim on-site environment, poor quality of mobile phone lenses, incorrect shooting methods and other reasons, about 20% of the photo images have low recognizability, which makes it impossible for companies to clearly judge the quality of sales personnel's visits.

[0003] The traditional method of enhancing image recognizability is generally to increase the overall brightness of the photo to achieve the purpose of increasing the image recognizability. However, since the brightness of all areas and all photographed objects in the image is enhanced indiscriminately, the image recognizability is often not substantially enhanced, and the image recognizability enhancement effect is poor. Summary of the invention

[0004] Based on this, it is necessary to provide a method for enhancing image recognizability in view of the problem that the image recognizability of the traditional method for enhancing image recognizability is not substantially enhanced and the enhancement effect of the image recognizability is poor.

[0005] The present application provides a method for enhancing image recognizability, comprising:

[0006] Acquire an image to be processed, and convert the image to be processed into a digital image;

[0007] Performing global histogram equalization processing on the digital image to increase the overall contrast of the digital image to obtain a first processed image;

[0008] Dividing the first processed image into a plurality of comparison regions, and performing a similarity calculation on each two adjacent comparison regions;

[0009] According to the similarity calculation result, two adjacent comparison areas whose similarity is greater than or equal to the similarity threshold are merged into the same merged area, so as to merge the multiple comparison areas and generate a second processed image composed of the multiple merged areas;

[0010] Perform pseudo color enhancement processing on the second processed image to generate a third processed image and output it.

[0011] Furthermore, a global histogram equalization process is performed on the digital image, including:

[0012] Converting the digital image into a grayscale histogram;

[0013] Calculate the number of pixels of each gray level in the grayscale histogram, the width of the rectangular histogram corresponding to the gray level, and the height of the rectangular histogram corresponding to the gray level;

[0014] Calculate the grayscale distribution function after global histogram equalization processing according to formula 1;

[0015]

[0016] Wherein, f(x) is the grayscale distribution function after global histogram equalization processing, L is the grayscale in the digital image, and x i is the i-th gray level in the histogram, h(x i ) is the gray level x in the gray histogram i The number of pixels, w is the gray level x i The width of the corresponding rectangular histogram, h is the gray level x i The height of the corresponding rectangular square;

[0017] According to the grayscale distribution function after the global histogram equalization processing, the grayscale of the digital image is adjusted to generate a first processed image.

[0018] Furthermore, the first processed image is divided into a plurality of comparison regions, and a similarity calculation is performed on each two adjacent comparison regions, including:

[0019] Taking each pixel in the first processed image as a comparison area, and then dividing the first processed image into a plurality of comparison areas;

[0020] Select two adjacent comparison areas, calculate the color similarity of the two adjacent comparison areas, and generate a color similarity score between the two adjacent comparison areas;

[0021] Calculating the texture similarity of two adjacent comparison areas to generate a texture similarity score between the two adjacent comparison areas;

[0022] Sum the color similarity score and the texture similarity score to generate the similarity score of two adjacent comparison areas;

[0023] The aforementioned steps of selecting two adjacent comparison regions and calculating the similarity scores are repeatedly performed until the similarity scores of all two adjacent comparison regions are calculated.

[0024] Furthermore, two adjacent comparison areas are selected, and color similarity calculation is performed on the two adjacent comparison areas, including:

[0025] According to the color distribution of two adjacent comparison areas, the color histograms corresponding to the two adjacent comparison areas are generated respectively; in each color histogram, 5 pixels are used as a color interval, and a total of 51 color intervals are divided;

[0026] In each color histogram, get the total number of pixels and the number of pixels falling in each color interval;

[0027] Select a color interval, and in each color histogram, calculate the color score of the color interval in each color histogram according to Formula 2;

[0028]

[0029] Among them, A n is the color score of the color interval, α n is the number of pixels in the color histogram that fall into the color interval, α is the total number of pixels in the color histogram, and n is the serial number of the color interval;

[0030] Compare the color scores of the color interval in the two color histograms, and take the color score with the smaller value as the color similarity score of the color interval;

[0031] Repeat the steps of selecting the color area and calculating the color similarity score to generate a color similarity score for each color interval;

[0032] S326, summing the color similarity scores of the respective color regions, and using the summation result as the color similarity score between two adjacent comparison regions.

[0033] Furthermore, the texture similarity calculation is performed on two adjacent comparison areas, including:

[0034] A texture value is extracted from each channel of each pixel point in two adjacent comparison areas to generate texture histograms corresponding to the two adjacent comparison areas; in each texture histogram, 5 pixels are used as a texture value interval, which is divided into 51 texture value intervals in total;

[0035] In each texture histogram, obtain the total number of pixels and the number of pixels falling in each texture value interval;

[0036] Select a texture value interval, and in each texture histogram, calculate the texture score of the texture value interval in each texture histogram according to Formula 3;

[0037]

[0038] Among them, B m is the texture score of the texture value interval, η m is the number of pixels in the texture histogram that fall within the texture value interval, n is the total number of pixels in the texture histogram, and m is the sequence number of the texture value interval;

[0039] Compare the texture scores of the texture value interval in the two texture histograms, and use the texture score with a smaller value as the texture similarity score of the texture value interval;

[0040] Repeating the above steps of selecting the texture value interval and calculating the texture similarity score to generate a texture similarity score for each texture value interval;

[0041] The texture similarity scores of each texture value region are summed up, and the sum result is used as the texture similarity score between two adjacent comparison regions.

[0042] Further, based on the similarity calculation result, two adjacent comparison regions whose similarity is greater than or equal to the similarity threshold are merged into the same merged region, including:

[0043] Select two adjacent comparison areas, and determine whether the similarity scores of the two adjacent comparison areas are greater than or equal to a similarity threshold;

[0044] If the similarity scores of two adjacent comparison regions are greater than or equal to the similarity threshold, the two adjacent comparison regions are determined to be similar, and the two adjacent comparison regions are merged into the same merged region;

[0045] Return to the step of selecting two adjacent comparison areas until all two adjacent comparison areas have been compared once between the similarity scores and the similarity threshold, thereby generating a second processed image consisting of a plurality of merged areas.

[0046] Further, merging two adjacent comparison regions whose similarity is greater than or equal to a similarity threshold into a same merged region also includes:

[0047] If the similarity scores of the two adjacent comparison regions are less than the similarity threshold, it is determined that the two adjacent comparison regions are independent of each other, and the process returns to the step of selecting the two adjacent comparison regions.

[0048] Further, performing pseudo color enhancement processing on the second processed image includes:

[0049] Performing grayscale layering processing on the second processed image, wherein the second processed image after the grayscale layering processing has a plurality of grayscale intervals;

[0050] Select a grayscale area, perform red transformation, green transformation and blue transformation on the grayscale area respectively; send the result of red transformation to the red channel, send the result of green transformation to the blue channel, and send the result of blue transformation to the blue channel;

[0051] The aforementioned steps of selecting grayscale areas and transforming colors are repeatedly performed until all grayscale areas have completed the red, green and blue transformation, thereby generating a third processed image.

[0052] The present application also provides a device for enhancing image recognizability, comprising:

[0053] An image conversion module, used for acquiring an image to be processed and converting the image to be processed into a digital image;

[0054] A histogram equalization processing module, connected to the image conversion module, is used to perform global histogram equalization processing on the digital image to increase the overall contrast of the digital image to obtain a first processed image;

[0055] A region division module, connected to the histogram equalization processing module, for dividing the first processed image into a plurality of comparison regions, and performing a similarity calculation for each two adjacent comparison regions;

[0056] A region merging module, connected to the region dividing module, is used to merge two adjacent comparison regions whose similarity is greater than or equal to the similarity threshold into the same merged region according to the similarity calculation result, so as to merge the multiple comparison regions and generate a second processed image composed of the multiple merged regions;

[0057] The pseudo color enhancement module is connected to the region merging module and is used to perform pseudo color enhancement processing on the second processed image to generate a third processed image and output it.

[0058] The present application also provides a computer-readable storage medium, comprising computer instructions. When the computer instructions are executed on the device for enhancing image recognizability as described above, the device for enhancing image recognizability executes the method for enhancing image recognizability as mentioned above.

[0059] The present application relates to a method, device and readable storage medium for enhancing the recognizability of an image, and by performing global histogram equalization processing on the image, the contrast of the entire image is increased. By dividing the image into multiple comparison areas, two adjacent comparison areas with high similarity are merged to achieve the distinction and recognition of local details of the image. The present application enhances the image from the overall image and the local details of the image, greatly increasing the recognition rate of image features, and can effectively identify objects in the image and the environment in which the objects are located. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 A schematic diagram of a flow chart of a method for enhancing image recognizability provided in one embodiment of the present application;

[0061] Figure 2 A schematic diagram of the structure of a device for enhancing image recognizability provided in one embodiment of the present application. DETAILED DESCRIPTION

[0062] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. 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.

[0063] The present application provides a method for enhancing image recognizability. It should be noted that the method for enhancing image recognizability provided by the present application is applicable to images captured by any device.

[0064] In addition, the method for enhancing image recognizability provided in the present application does not limit its execution subject. Optionally, the execution subject of the method for enhancing image recognizability provided in the present application may be a device for enhancing image recognizability. Specifically, the execution subject of the method for enhancing image recognizability provided in the present application may be one or more processors in the device for enhancing image recognizability.

[0065] like Figure 1 As shown, in one embodiment of the present application, the method for enhancing image recognizability includes the following steps S100 to S500:

[0066] S100, obtaining an image to be processed, and converting the image to be processed into a digital image.

[0067] S200, performing global histogram equalization processing on the digital image to increase the overall contrast of the digital image to obtain a first processed image.

[0068] S300: Divide the first processed image into a plurality of comparison regions, and perform a similarity calculation on every two adjacent comparison regions.

[0069] S400 , according to the similarity calculation result, two adjacent comparison areas whose similarity is greater than or equal to the similarity threshold are merged into the same merged area, so as to merge the multiple comparison areas and generate a second processed image composed of the multiple merged areas.

[0070] S500, performing pseudo color enhancement processing on the second processed image to generate a third processed image and output it.

[0071] Specifically, in step S100, the device for enhancing image recognizability obtains an externally input image to be processed. The image to be processed is a continuous-tone analog image. The device for enhancing image recognizability can convert the image to be processed into a digital image after sampling and quantization, so as to be processed by a processor of the device for enhancing image recognizability.

[0072] In this embodiment, the image is subjected to global histogram equalization processing to increase the contrast of the entire image. The image is divided into multiple comparison areas, and two adjacent comparison areas with high similarity are merged to distinguish and identify the local details of the image. The present application enhances the image as a whole and in local details, greatly increasing the recognition rate of image features, and can effectively identify objects in the image and the environment in which the objects are located.

[0073] In one embodiment of the present application, step S200 includes the following steps S210 to S240:

[0074] S210, converting the digital image into a grayscale histogram.

[0075] S220, calculating the number of pixels of each gray level in the gray level histogram, the width of the rectangular histogram corresponding to the gray level, and the height of the rectangular histogram corresponding to the gray level.

[0076] S230, calculating the gray level distribution function after global histogram equalization processing according to Formula 1.

[0077]

[0078] Wherein, f(x) is the grayscale distribution function after global histogram equalization processing. L is the grayscale in the digital image. x i is the i-th gray level in the histogram. i ) is the gray level x in the gray histogram i Image

[0079] The number of pixels. w is the gray level x i The width of the corresponding rectangular histogram. h is the gray level x i The height of the corresponding rectangle.

[0080] S240, adjusting the grayscale of the digital image according to the grayscale distribution function after the global histogram equalization processing to generate a first processed image.

[0081] Specifically, the purpose of this embodiment is to convert one or several relatively concentrated grayscale intervals in a digital image into a uniform distribution within the entire grayscale range, thereby enhancing the overall contrast of the digital image.

[0082] In this embodiment, the contrast of the entire image is increased by performing global histogram equalization processing on the image.

[0083] In one embodiment of the present application, step S300 includes the following steps S310 to S350:

[0084] S310, taking each pixel in the first processed image as a comparison area, and then dividing the first processed image into a plurality of comparison areas.

[0085] S320, selecting two adjacent comparison areas, calculating color similarity between the two adjacent comparison areas, and generating a color similarity score between the two adjacent comparison areas.

[0086] S330: Calculate texture similarity of two adjacent comparison regions to generate texture similarity scores between the two adjacent comparison regions.

[0087] S340 , summing the color similarity score and the texture similarity score to generate similarity scores of two adjacent comparison areas.

[0088] S350, repeatedly executing step S320 to step S340 until the similarity scores of all two adjacent comparison regions are calculated.

[0089] Specifically, for example, if the color similarity score of two adjacent comparison regions is 0.6 and the texture similarity score is 0.3, then the similarity score of the two adjacent comparison regions is 0.6+0.3=0.9.

[0090] In this embodiment, by dividing the first processed image into multiple comparison areas, the first processed image is divided into details, thereby achieving similarity comparison between every two adjacent comparison areas in the first processed image, providing a data basis for subsequent merging of comparison areas.

[0091] In one embodiment of the present application, step S320 includes the following steps S321 to S326:

[0092] S321, according to the color distribution of two adjacent comparison areas, respectively generate color histograms corresponding to the two adjacent comparison areas. In each color histogram, 5 pixels are used as a color interval, and a total of 51 color intervals are divided.

[0093] S322, in each color histogram, obtain the total number of pixels and the number of pixels falling in each color interval.

[0094] S323, selecting a color interval, and calculating the color score of the color interval in each color histogram according to Formula 2.

[0095]

[0096] Among them, A n is the color score of the color interval. n is the number of pixels in the color histogram that fall into the color interval. α is the total number of pixels in the color histogram. n is the serial number of the color interval.

[0097] S324, comparing the color scores of the color interval in the two color histograms, and taking the color score with a smaller value as the color similarity score of the color interval.

[0098] S325, repeatedly executing step S323 to step S324 to generate a color similarity score for each color interval.

[0099] S326, summing the color similarity scores of the respective color regions, and using the summation result as the color similarity score between two adjacent comparison regions.

[0100] Specifically, the color range of the color histogram is 0-255, with 5 pixels as a segment, and a total of 51 segments, representing 51 color intervals.

[0101] For example, in two adjacent comparison areas, there are 50 pixels in the color range 0-5 in the color histogram of comparison area A, and there are a total of 500 pixels in the color histogram of comparison area A. Then, the color score of the color range 0-5 of comparison area A is 0.1.

[0102] The calculation method for comparison area B is the same. If the color score of the 0-5 color range of comparison area B is 0.2 after calculation, since 0.1 is less than 0.2, 0.1 is taken as the color score of the 0-5 color range.

[0103] In this embodiment, by using a color histogram to calculate the color similarity score between two adjacent comparison areas, a scientific determination of the similarity between two adjacent comparison areas from a color dimension is achieved.

[0104] In one embodiment of the present application, the step S330 includes the following steps S331 to S500:

[0105] S331, extract a texture value from each channel of each pixel in two adjacent comparison areas, and generate texture histograms corresponding to the two adjacent comparison areas. In each texture histogram, 5 pixels are used as a texture value interval, and a total of 51 texture value intervals are divided.

[0106] S332, in each texture histogram, obtain the total number of pixels and the number of pixels falling in each texture value interval.

[0107] S333, selecting a texture value interval, and calculating the texture score of the texture value interval in each texture histogram according to Formula 3.

[0108]

[0109] Among them, B m is the texture score of the texture value interval. m is the number of pixels in the texture histogram that fall within the texture value interval. n is the total number of pixels in the texture histogram. m is the sequence number of the texture value interval.

[0110] S334, comparing the texture scores of the texture value interval in the two texture histograms, and taking the texture score with a smaller value as the texture similarity score of the texture value interval.

[0111] S335, repeatedly executing step S333 to step S334 to generate a texture similarity score for each texture value interval.

[0112] S336, summing up the texture similarity scores of the respective texture value regions, and using the summation result as the texture similarity score between two adjacent comparison regions.

[0113] Specifically, steps S331 to S336 in this embodiment are implemented according to the SIFI algorithm, and the specific steps are similar to the principles of steps S321 to S326 in the previous embodiment, and will not be repeated again.

[0114] In this embodiment, by using a texture value histogram to calculate the texture similarity score between two adjacent comparison areas, a scientific determination of the similarity of two adjacent comparison areas from a texture dimension is achieved.

[0115] In one embodiment of the present application, step S400 includes:

[0116] S410: Select two adjacent comparison regions and determine whether the similarity scores of the two adjacent comparison regions are greater than or equal to a similarity threshold.

[0117] S420: If the similarity scores of the two adjacent comparison regions are greater than or equal to the similarity threshold, the two adjacent comparison regions are determined to be similar, and the two adjacent comparison regions are merged into the same merged region.

[0118] S430, returning to step S410, until all two adjacent comparison areas have been compared once between the similarity scores and the similarity threshold, to generate a second processed image consisting of a plurality of merged areas.

[0119] In one embodiment of the present application, the step S400 further includes:

[0120] S421, if the similarity scores of the two adjacent comparison regions are less than the similarity threshold, it is determined that the two adjacent comparison regions are independent of each other, and the process returns to step S410.

[0121] Specifically, through the above two embodiments, all comparison areas can be traversed, and the entire first processed image can be repeatedly divided into several independent merged areas, so that the local details of the image can be distinguished and recognized, thereby enhancing the image recognizability.

[0122] In this embodiment, the image is divided into a plurality of comparison areas, and two adjacent comparison areas with high similarity are merged to achieve the distinction and recognition of local details of the image.

[0123] In one embodiment of the present application, step S500 includes:

[0124] S510, performing grayscale layering processing on the second processed image, and the second processed image after the grayscale layering processing has multiple grayscale intervals.

[0125] S520, selecting a grayscale area, and performing red transformation, green transformation and blue transformation on the grayscale area respectively.

[0126] S530, sending the result of red transformation into the red channel, sending the result of green transformation into the blue channel, and sending the result of blue transformation into the blue channel.

[0127] S540, repeatedly executing step S520 to step S530 until all grayscale areas complete the red, green and blue transformation, and generating a third processed image.

[0128] The present application also provides a device for enhancing image recognizability.

[0129] like Figure 2 As shown, in one embodiment of the present application, the device for enhancing image recognizability includes an image conversion module 10, a histogram equalization processing module 20, a region division module 30, a region merging module 40, and a pseudo color enhancement module 50.

[0130] The image conversion module 10 is used to obtain the image to be processed and convert the image to be processed into a digital image.

[0131] The histogram equalization processing module 20 is connected to the image conversion module 10. The histogram equalization processing module 20 is used to perform global histogram equalization processing on the digital image to increase the overall contrast of the digital image to obtain a first processed image.

[0132] The region division module 30 is connected to the histogram equalization processing module 20. The region division module 30 is used to divide the first processed image into a plurality of comparison regions, and perform a similarity calculation on each two adjacent comparison regions.

[0133] The region merging module 40 is connected to the region dividing module 30. The region merging module 10 is used to merge two adjacent comparison regions whose similarity is greater than or equal to the similarity threshold into the same merged region according to the similarity calculation result, so as to merge multiple comparison regions and generate a second processed image composed of multiple merged regions.

[0134] The pseudo color enhancement module 50 is connected to the region merging module 40. The pseudo color enhancement module 50 is used to perform pseudo color enhancement processing on the second processed image, generate a third processed image, and output it.

[0135] The present application also provides a computer-readable storage medium. The computer-readable storage medium includes computer instructions. When the computer instructions are executed on the device for enhancing image recognizability mentioned in the above content, the device for enhancing image recognizability executes the method for enhancing image recognizability mentioned in the above content.

[0136] The technical features of the above-described embodiments may be arbitrarily combined, and the execution order of the method steps is not limited. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0137] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be construed as limiting the scope of the present application. It should be noted that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for enhancing image recognizability, characterized in that: The method for enhancing image recognizability comprises: S100, acquiring an image to be processed, and converting the image to be processed into a digital image; S200, performing global histogram equalization processing on the digital image to increase the overall contrast of the digital image to obtain a first processed image; S300, dividing the first processed image into a plurality of comparison regions, and performing a similarity calculation on each two adjacent comparison regions; S400, merging two adjacent comparison regions whose similarity is greater than or equal to a similarity threshold into a same merged region according to a similarity calculation result, so as to merge multiple comparison regions and generate a second processed image composed of multiple merged regions; S500, performing pseudo color enhancement processing on the second processed image to generate a third processed image and output it, including: S510, performing grayscale layering processing on the second processed image, whereby the second processed image after the grayscale layering processing has a plurality of grayscale intervals; S520, selecting a grayscale area, and performing red transformation, green transformation, and blue transformation on the grayscale area respectively; S530, sending the result of red transformation into the red channel, sending the result of green transformation into the blue channel, and sending the result of blue transformation into the blue channel; S540, repeatedly executing step S520 to step S530 until all grayscale areas complete the red, green and blue transformation, and generating a third processed image.

2. The method for enhancing image recognizability according to claim 1, characterized in that: The step S200 includes: S210, converting the digital image into a grayscale histogram; S220, calculating the number of pixels of each gray level in the gray histogram, the width of the rectangular histogram corresponding to the gray level, and the height of the rectangular histogram corresponding to the gray level; S230, calculating the gray level distribution function after global histogram equalization processing according to Formula 1; Wherein, f(x) is the grayscale distribution function after global histogram equalization processing, L is the grayscale in the digital image, and x i is the i-th gray level in the histogram, h(x i ) is the gray level x in the gray histogram i The number of pixels, w is the gray level x i The width of the corresponding rectangular histogram, h is the gray level x i The height of the corresponding rectangular square; S240, adjusting the grayscale of the digital image according to the grayscale distribution function after the global histogram equalization processing to generate a first processed image.

3. The method for enhancing image recognizability according to claim 2, characterized in that: The step S300 includes: S310, taking each pixel in the first processed image as a comparison area, and then dividing the first processed image into a plurality of comparison areas; S320, selecting two adjacent comparison areas, calculating color similarity between the two adjacent comparison areas, and generating a color similarity score between the two adjacent comparison areas; S330, calculating texture similarity of two adjacent comparison areas to generate texture similarity scores between the two adjacent comparison areas; S340, summing the color similarity score and the texture similarity score to generate similarity scores of two adjacent comparison areas; S350, repeatedly executing step S320 to step S340 until the similarity scores of all two adjacent comparison regions are calculated.

4. The method for enhancing image recognizability according to claim 3, characterized in that: The step S320 includes: S321, generating color histograms corresponding to the two adjacent comparison areas respectively according to the color distribution conditions of the two adjacent comparison areas; in each color histogram, 5 pixels are used as one color interval, and a total of 51 color intervals are divided; S322, in each color histogram, obtaining the total number of pixels and the number of pixels falling in each color interval; S323, selecting a color interval, and calculating the color score of the color interval in each color histogram according to Formula 2; Among them, A n is the color score of the color interval, α n is the number of pixels in the color histogram that fall into the color interval, α is the total number of pixels in the color histogram, and n is the serial number of the color interval; S324, comparing the color scores of the color interval in the two color histograms, and taking the color score with a smaller value as the color similarity score of the color interval; S325, repeatedly executing steps S323 to S324 to generate a color similarity score for each color interval; S326, summing the color similarity scores of the respective color regions, and using the summation result as the color similarity score between two adjacent comparison regions.

5. The method for enhancing image recognizability according to claim 4, characterized in that: The step S330 includes: S331, extracting a texture value from each channel of each pixel in two adjacent comparison areas, and generating texture histograms corresponding to the two adjacent comparison areas; in each texture histogram, 5 pixels are used as a texture value interval, and a total of 51 texture value intervals are divided; S332, in each texture histogram, obtaining the total number of pixels and the number of pixels falling in each texture value interval; S333, selecting a texture value interval, and calculating the texture score of the texture value interval in each texture histogram according to Formula 3; Among them, B m is the texture score of the texture value interval, η m is the number of pixels in the texture histogram that fall within the texture value interval, n is the total number of pixels in the texture histogram, and m is the sequence number of the texture value interval; S334, comparing the texture scores of the texture value interval in the two texture histograms, and taking the texture score with a smaller value as the texture similarity score of the texture value interval; S335, repeatedly executing step S333 to step S334 to generate a texture similarity score for each texture value interval; S336, summing up the texture similarity scores of the respective texture value regions, and using the summation result as the texture similarity score between two adjacent comparison regions.

6. The method for enhancing image recognizability according to claim 5, characterized in that: The step S400 includes: S410, selecting two adjacent comparison regions, and determining whether the similarity scores of the two adjacent comparison regions are greater than or equal to a similarity threshold; S420, if the similarity scores of the two adjacent comparison regions are greater than or equal to the similarity threshold, the two adjacent comparison regions are determined to be similar, and the two adjacent comparison regions are merged into the same merged region; S430, returning to step S410, until all two adjacent comparison areas have been compared once between the similarity scores and the similarity threshold, to generate a second processed image consisting of a plurality of merged areas.

7. The method for enhancing image recognizability according to claim 6, characterized in that: The step S400 further includes: S421, if the similarity scores of the two adjacent comparison regions are less than the similarity threshold, it is determined that the two adjacent comparison regions are independent of each other, and the process returns to step S410.

8. A device for enhancing image recognizability, characterized in that: include: An image conversion module, used for acquiring an image to be processed and converting the image to be processed into a digital image; A histogram equalization processing module, connected to the image conversion module, is used to perform global histogram equalization processing on the digital image to increase the overall contrast of the digital image to obtain a first processed image; A region division module, connected to the histogram equalization processing module, for dividing the first processed image into a plurality of comparison regions, and performing a similarity calculation on each two adjacent comparison regions; A region merging module, connected to the region dividing module, is used to merge two adjacent comparison regions whose similarity is greater than or equal to the similarity threshold into the same merged region according to the similarity calculation result, so as to merge the multiple comparison regions and generate a second processed image composed of the multiple merged regions; a pseudo color enhancement module, connected to the region merging module, for performing pseudo color enhancement processing on the second processed image, generating a third processed image and outputting the image; Among them, the pseudo color enhancement module includes: S510, performing grayscale layering processing on the second processed image, whereby the second processed image after the grayscale layering processing has a plurality of grayscale intervals; S520, selecting a grayscale area, and performing red transformation, green transformation, and blue transformation on the grayscale area respectively; S530, sending the result of red transformation into the red channel, sending the result of green transformation into the blue channel, and sending the result of blue transformation into the blue channel; S540, repeatedly executing step S520 to step S530 until all grayscale areas complete the red, green and blue transformation, and generating a third processed image.

9. A computer-readable storage medium, characterized in that: The method comprises computer instructions, which, when executed on the apparatus for enhancing image recognizability as claimed in claim 8, enable the apparatus for enhancing image recognizability to execute the method for enhancing image recognizability as claimed in any one of claims 1 to 7.

Images