CN111242879A - Image processing method, apparatus, electronic device, and medium - Google Patents

Abstract

The present disclosure provides an image processing method, including: acquiring an original image, wherein the original image includes an original histogram; processing the original image to obtain an edge image and a non-edge image; processing the edge image and the edge image respectively a non-edge image, obtaining an edge histogram of the edge image and a non-edge histogram of the non-edge image; processing the edge histogram and the non-edge histogram to obtain a fusion histogram; and based on the fusion histogram The original histogram is processed to obtain a processed histogram to obtain a processed image from the processed histogram, wherein the contrast of the processed image is higher than the contrast of the original image. The present disclosure also provides an image processing apparatus, an electronic device, and a computer-readable storage medium.

Description

Image processing method, apparatus, electronic device, and medium

technical field

The present disclosure relates to an image processing method, an image processing apparatus, an electronic device, and a computer-readable storage medium.

Background technique

Medical imaging systems play an important role in clinical work, and improving the quality of medical images is crucial to helping doctors obtain more patient information. Often times, image quality is significantly reduced, such as darker images or lower image contrast, due to lack of operator expertise, uneven image capture equipment, uneven lighting, etc.

SUMMARY OF THE INVENTION

One aspect of the present disclosure provides an image processing method, including: acquiring an original image, wherein the original image includes an original histogram, processing the original image to obtain an edge image and a non-edge image, and processing the edge image respectively and the non-edge image, obtain the edge histogram of the edge image and the non-edge histogram of the non-edge image, process the edge histogram and the non-edge histogram to obtain a fusion histogram, based on the The fusion histogram processes the original histogram to obtain a processed histogram to obtain a processed image from the processed histogram, wherein the contrast of the processed image is higher than the contrast of the original image.

Optionally, the above-mentioned processing of the edge histogram and the non-edge histogram to obtain a fusion histogram includes: segmenting the edge histogram and the non-edge histogram respectively to obtain the edge histogram The M segments of , and the N segments of the non-edge histogram, where M is an integer greater than 1, and N is an integer greater than 1, and the M segments are processed respectively to obtain the processed edge histogram. Each segment is processed to obtain a processed non-edge histogram, and the processed edge histogram and the processed non-edge histogram are fused to obtain the fused histogram.

Optionally, the above-mentioned processing of the M segments respectively to obtain the processed edge histogram includes: determining the segment shift distance of each segment in the M segments, and obtaining M segment shift distances, based on the M segment shift distances. The segment shift distance performs shift processing on the M segments respectively, and sequentially determines each segment in the M segments as a first segment, wherein the first segment includes m grayscale values, and the Each gray value in the m gray values has a corresponding number of pixels, m is an integer greater than or equal to 1, and the gray value shift distance of each gray value in the m gray values is determined , to obtain m gray value shift distances, and respectively perform shift processing on the m gray value values based on the m gray value shift distances to obtain the processed edge histogram.

Optionally, the above-mentioned processing of the N segments respectively to obtain the processed non-edge histogram includes: determining the segment shift distance of each segment in the N segments to obtain N segment shift distances, based on the N segment shift distances. Perform shift processing on the N segments respectively by the segment shift distances, and sequentially determine each segment in the N segments as a second segment, wherein the second segment includes n grayscale values, so Each gray value in the n gray values has a corresponding number of pixels, n is an integer greater than or equal to 1, and the gray value shift of each gray value in the n gray values is determined. distance, to obtain n gray value shift distances, and respectively perform shift processing on the n gray value values based on the n gray value shift distances to obtain the processed non-edge histogram.

Optionally, the above-mentioned determining the fragment shift distance of each of the M fragments includes: according to the number of pixels in each of the M fragments, the number of fragments M of the edge histogram, the edge The total number of pixels in the histogram is calculated to obtain the segment shift distance of each segment in the M segments. The determining the gray value shift distance of each gray value in the m gray values includes: according to the number of pixels of each gray value in the m gray values, the gray value of the first segment The number m of degree values and the total number of pixels of the first segment are calculated to obtain the gray value shift distance of each gray value in the m gray values.

Optionally, the above-mentioned determining the fragment shift distance of each of the N fragments includes: according to the number of pixels in each of the N fragments, the number of fragments N of the edge histogram, the edge The total number of pixels in the histogram is calculated to obtain the segment shift distance of each segment in the N segments. The determining the gray value shift distance of each gray value in the n gray values includes: according to the number of pixels of each gray value in the n gray values, the gray value of the first segment The number of degree values n and the total number of pixels of the first segment are calculated to obtain the gray value shift distance of each gray value in the n gray values.

Optionally, performing segmentation processing on the edge histogram and the non-edge histogram respectively, and obtaining M segments of the edge histogram and N segments of the non-edge histogram includes: calculating the The first sparse value of the edge histogram and the second sparse value of the non-edge histogram, wherein the first sparse value is used to represent the degree of deviation of the number of pixels in the edge histogram, the second sparse value The sparse value is used to characterize the degree of deviation of the number of pixels in the non-edge histogram, and determine p gray values corresponding to the number of pixels in the edge histogram that are smaller than the first sparse value, where p is an integer greater than or equal to 1, determine the q grayscale values corresponding to the number of pixels in the non-edge histogram less than the second sparse value, where q is an integer greater than or equal to 1, and the p grayscale values The value is used as a breakpoint, and M segments are obtained by segmenting the edge histogram, and the q gray values are used as a breakpoint, and N segments are obtained by segmenting the non-edge histogram.

Optionally, the above-mentioned processing of the original histogram based on the fusion histogram to obtain the processed histogram includes: determining the cumulative distribution function of the fusion histogram, determining the cumulative distribution function of the original histogram, and calculating the fusing the cumulative distribution function of the histogram and the cumulative distribution function of the original histogram to obtain a gray value change relationship, wherein the gray value change relationship includes an enhancement corresponding to each gray value in the original histogram Gray value, based on the gray value change relationship, moving each gray value in the original histogram to the corresponding enhanced gray value to obtain a processed histogram.

Optionally, the above-mentioned processing of the original image to obtain an edge image and a non-edge image includes: calculating the gradient value of each pixel in the original image, and determining that the pixel whose gradient value is greater than a preset gradient value is used as the edge image. and determine the pixels whose gradient value is less than or equal to the preset gradient value as the pixels in the non-edge image.

Optionally, the above method further includes: before processing the original image to obtain an edge image and a non-edge image, filtering the original image by using a Gaussian filtering method, so as to remove at least part of the noise in the original image information.

Another aspect of the present disclosure provides an image processing apparatus, including: an acquisition module, a first processing module, a second processing module, a third processing module, and a fourth processing module. Wherein, the acquiring module acquires an original image, wherein the original image includes an original histogram. The first processing module processes the original image to obtain an edge image and a non-edge image. The second processing module processes the edge image and the non-edge image respectively to obtain an edge histogram of the edge image and a non-edge histogram of the non-edge image. The third processing module processes the edge histogram and the non-edge histogram to obtain a fusion histogram. a fourth processing module that processes the original histogram based on the fused histogram to obtain a processed histogram to obtain a processed image from the processed histogram, wherein the processed image has a higher contrast than the Contrast of the original image.

Optionally, the above-mentioned processing of the edge histogram and the non-edge histogram to obtain a fusion histogram includes: segmenting the edge histogram and the non-edge histogram respectively to obtain the edge histogram The M segments of , and the N segments of the non-edge histogram, where M is an integer greater than 1, and N is an integer greater than 1, and the M segments are processed respectively to obtain the processed edge histogram. Each segment is processed to obtain a processed non-edge histogram, and the processed edge histogram and the processed non-edge histogram are fused to obtain the fused histogram.

Optionally, the above-mentioned processing of the M segments respectively to obtain the processed edge histogram includes: determining the segment shift distance of each segment in the M segments, and obtaining M segment shift distances, based on the M segment shift distances. The segment shift distance performs shift processing on the M segments respectively, and sequentially determines each segment in the M segments as a first segment, wherein the first segment includes m grayscale values, and the Each gray value in the m gray values has a corresponding number of pixels, m is an integer greater than or equal to 1, and the gray value shift distance of each gray value in the m gray values is determined , to obtain m gray value shift distances, and respectively perform shift processing on the m gray value values based on the m gray value shift distances to obtain the processed edge histogram.

Optionally, the above-mentioned processing of the N segments respectively to obtain the processed non-edge histogram includes: determining the segment shift distance of each segment in the N segments to obtain N segment shift distances, based on the N segment shift distances. Perform shift processing on the N segments respectively by the segment shift distances, and sequentially determine each segment in the N segments as a second segment, wherein the second segment includes n grayscale values, so Each gray value in the n gray values has a corresponding number of pixels, n is an integer greater than or equal to 1, and the gray value shift of each gray value in the n gray values is determined. distance, to obtain n gray value shift distances, and respectively perform shift processing on the n gray value values based on the n gray value shift distances to obtain the processed non-edge histogram.

Optionally, the above-mentioned determining the fragment shift distance of each of the M fragments includes: according to the number of pixels in each of the M fragments, the number of fragments M of the edge histogram, the edge The total number of pixels in the histogram is calculated to obtain the segment shift distance of each segment in the M segments. The determining the gray value shift distance of each gray value in the m gray values includes: according to the number of pixels of each gray value in the m gray values, the gray value of the first segment The number m of degree values and the total number of pixels of the first segment are calculated to obtain the gray value shift distance of each gray value in the m gray values.

Optionally, the above-mentioned determining the fragment shift distance of each of the N fragments includes: according to the number of pixels in each of the N fragments, the number of fragments N of the edge histogram, the edge The total number of pixels in the histogram is calculated to obtain the segment shift distance of each segment in the N segments. The determining the gray value shift distance of each gray value in the n gray values includes: according to the number of pixels of each gray value in the n gray values, the gray value of the first segment The number of degree values n and the total number of pixels of the first segment are calculated to obtain the gray value shift distance of each gray value in the n gray values.

Optionally, performing segmentation processing on the edge histogram and the non-edge histogram respectively, and obtaining M segments of the edge histogram and N segments of the non-edge histogram includes: calculating the The first sparse value of the edge histogram and the second sparse value of the non-edge histogram, wherein the first sparse value is used to represent the degree of deviation of the number of pixels in the edge histogram, the second sparse value The sparse value is used to characterize the degree of deviation of the number of pixels in the non-edge histogram, and determine p gray values corresponding to the number of pixels in the edge histogram that are smaller than the first sparse value, where p is an integer greater than or equal to 1, determine the q grayscale values corresponding to the number of pixels in the non-edge histogram less than the second sparse value, where q is an integer greater than or equal to 1, and the p grayscale values The value is used as a breakpoint, and M segments are obtained by segmenting the edge histogram, and the q gray values are used as a breakpoint, and N segments are obtained by segmenting the non-edge histogram.

Optionally, the above-mentioned processing of the original histogram based on the fusion histogram to obtain the processed histogram includes: determining the cumulative distribution function of the fusion histogram, determining the cumulative distribution function of the original histogram, and calculating the fusing the cumulative distribution function of the histogram and the cumulative distribution function of the original histogram to obtain a gray value change relationship, wherein the gray value change relationship includes an enhancement corresponding to each gray value in the original histogram Gray value, based on the gray value change relationship, moving each gray value in the original histogram to the corresponding enhanced gray value to obtain a processed histogram.

Optionally, the above-mentioned processing of the original image to obtain an edge image and a non-edge image includes: calculating the gradient value of each pixel in the original image, and determining that the pixel whose gradient value is greater than a preset gradient value is used as the edge image. and determine the pixels whose gradient value is less than or equal to the preset gradient value as the pixels in the non-edge image.

Optionally, the above-mentioned apparatus further includes: a fifth processing module, which uses Gaussian filtering to filter the original image before processing the original image to obtain the edge image and the non-edge image, so as to remove the original image. at least part of the noise information in .

Another aspect of the present disclosure provides an electronic device, comprising: one or more processors; a memory for storing one or more programs, wherein when the one or more programs are executed by the one or more programs The processor, when executed, causes the one or more processors to implement the method as above.

Another aspect of the present disclosure provides a non-volatile readable storage medium storing computer-executable instructions that, when executed, are used to implement the above method.

Another aspect of the present disclosure provides a computer-readable storage medium storing computer-executable instructions, which when executed, are used to implement the above method.

Description of drawings

For a more complete understanding of the present disclosure and its advantages, reference will now be made to the following description taken in conjunction with the accompanying drawings, in which:

FIG. 1 schematically shows a flowchart of an image processing method according to an embodiment of the present disclosure;

2 to 3 schematically show schematic diagrams of performing segmentation processing on an edge histogram according to an embodiment of the present disclosure;

FIG. 4 schematically shows a schematic diagram of performing shift processing on M segments according to an embodiment of the present disclosure;

FIG. 5 schematically shows a schematic diagram of performing shift processing on grayscale values in each of the M segments according to an embodiment of the present disclosure;

FIG. 6 schematically shows a block diagram of an image processing apparatus according to an embodiment of the present disclosure; and

FIG. 7 schematically shows a block diagram of a computer system for implementing image processing according to an embodiment of the present disclosure.

Detailed ways

Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. It should be understood, however, that these descriptions are exemplary only, and are not intended to limit the scope of the present disclosure. In the following detailed description, for convenience of explanation, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the present disclosure. It will be apparent, however, that one or more embodiments may be practiced without these specific details. Also, in the following description, descriptions of well-known structures and techniques are omitted to avoid unnecessarily obscuring the concepts of the present disclosure.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the present disclosure. The terms "comprising", "comprising" and the like as used herein indicate the presence of stated features, steps, operations and/or components, but do not preclude the presence or addition of one or more other features, steps, operations or components.

All terms (including technical and scientific terms) used herein have the meaning as commonly understood by one of ordinary skill in the art, unless otherwise defined. It should be noted that terms used herein should be construed to have meanings consistent with the context of the present specification and should not be construed in an idealized or overly rigid manner.

Where expressions like "at least one of A, B, and C, etc.," are used, they should generally be interpreted in accordance with the meaning of the expression as commonly understood by those skilled in the art (eg, "has A, B, and C") At least one of the "systems" shall include, but not be limited to, systems with A alone, B alone, C alone, A and B, A and C, B and C, and/or A, B, C, etc. ). Where expressions like "at least one of A, B, or C, etc.," are used, they should generally be interpreted in accordance with the meaning of the expression as commonly understood by those skilled in the art (eg, "has A, B, or C, etc." At least one of the "systems" shall include, but not be limited to, systems with A alone, B alone, C alone, A and B, A and C, B and C, and/or A, B, C, etc. ).

Some block diagrams and/or flow diagrams are shown in the figures. It will be understood that some of the blocks in the block diagrams and/or flowcharts, or combinations thereof, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer or other programmable control device such that the instructions, when executed by the processor, may be created to implement the functions illustrated in the block diagrams and/or flow diagrams/ operating device.

Accordingly, the techniques of this disclosure may be implemented in hardware and/or software (including firmware, microcode, etc.). Additionally, the techniques of the present disclosure may take the form of a computer program product on a computer-readable medium having stored instructions for use by or in conjunction with an instruction execution system. In the context of this disclosure, a computer-readable medium can be any medium that can contain, store, communicate, propagate, or transmit instructions. For example, a computer-readable medium may include, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, device, or propagation medium. Specific examples of computer-readable media include: magnetic storage devices, such as magnetic tapes or hard disks (HDDs); optical storage devices, such as compact disks (CD-ROMs); memories, such as random access memory (RAM) or flash memory; and/or wired /Wireless communication link.

An embodiment of the present disclosure provides an image processing method, including: acquiring an original image, wherein the original image includes an original histogram, and processing the original image to obtain an edge image and a non-edge image. Then, process the edge image and the non-edge image respectively to obtain the edge histogram of the edge image and the non-edge histogram of the non-edge image, and process the edge histogram and the non-edge histogram to obtain the fusion histogram. Thereafter, the original histogram is processed based on the fused histogram, resulting in a processed histogram to obtain a processed image from the processed histogram, wherein the contrast of the processed image is higher than that of the original image.

FIG. 1 schematically shows a flowchart of an image processing method according to an embodiment of the present disclosure.

As shown in FIG. 1 , the image processing method includes, for example, operations S110 to S150.

In operation S110, an original image is obtained, wherein the original image includes an original histogram.

According to the embodiment of the present disclosure, the original image may be, for example, a medical image. When displaying a medical image, it is often necessary to perform enhancement processing on the medical image to increase the difference between different tissues and organs in the medical image, thereby improving the visual effect of the medical image. .

According to the embodiment of the present disclosure, before processing the original image to obtain the edge image and the non-edge image, the original image may be filtered by using a Gaussian filtering method, so as to remove at least part of noise information in the original image.

For example, the original image includes an original histogram, which can be smoothed with a two-dimensional Gaussian function in order to eliminate noise interference. Among them, noise interference, for example, refers to the fact that in practical applications, medical images have noise due to random fluctuations in gray levels or non-uniform illumination, resulting in sparse peaks and valleys in the image histogram. The two-dimensional Gaussian function is, for example, shown in formula (1).

Among them, x and y in formula (1) represent the coordinate position of the pixel in the original image, and σ represents the standard deviation. In one embodiment, the size of the Gaussian convolution kernel may be set to 3×3, and the standard deviation σ=0.85. It can be understood that those skilled in the art can set the size of the Gaussian convolution kernel and the value of the standard deviation according to the actual application.

In operation S120, the original image is processed to obtain an edge image and a non-edge image, and the specific process is described as follows.

For example, first calculate the gradient value of each pixel in the original image. For example, the image function of the original image is f(x, y), and the gradient vector defining the original image is formula (2).

Among them, G _x represents the approximate value of the horizontal grayscale difference of each pixel in the original image, and G _y represents the approximate value of the vertical grayscale difference of each pixel in the original image. As shown in formula (3), G _x and G _y can be calculated by convolving the original image with a set of 3x3 filters, where M _g represents the original image.

Then, for each pixel in the original image, the gradient value G of each pixel can be calculated by combining the horizontal grayscale difference approximation G _x and the vertical grayscale difference approximate value G _y of each pixel. The calculation process of the gradient value G is as shown in the formula (4).

Finally, pixels with gradient values greater than the preset gradient value may be determined as pixels in the edge image, and pixels with gradient values less than or equal to the preset gradient value may be determined as pixels in the non-edge image. Wherein, in an embodiment, the preset gradient value may be 1, for example. If the gradient value G>1 of a pixel in the original image is determined as an edge point, if the gradient value of a pixel in the original image G≤1, then the pixel is determined as a non-edge point, thus obtaining an edge images and non-edge images. It can be understood that those skilled in the art can set the value of the preset gradient value according to the actual application.

In operation S130, the edge image and the non-edge image are respectively processed to obtain an edge histogram of the edge image and a non-edge histogram of the non-edge image. For example, after the edge image and the non-edge image are obtained, the edge image and the non-edge image can be processed respectively to obtain the corresponding edge histogram and non-edge histogram.

In operation S140, the edge histogram and the non-edge histogram are processed to obtain a fusion histogram, and the specific process is described as follows.

For example, the edge histogram and the non-edge histogram are segmented respectively to obtain M segments of the edge histogram and N segments of the non-edge histogram, where M is an integer greater than 1, and N is an integer greater than 1.

2 to 3 schematically show schematic diagrams of segmenting an edge histogram according to an embodiment of the present disclosure.

The following describes the M segments of the edge histogram obtained by segmenting the edge histogram with reference to FIG. 2 to FIG. 3 .

First, the first sparse value of the edge histogram is calculated, and the first sparse value is used to represent the degree of deviation of the number of pixels in the edge histogram. Among them, the first sparse value E is:

表示边缘直方图中各个灰度值对应像素个数的均值。对于边缘直方图来说，

表示该边缘直方图的像素的平均值，例如，如果i的取值为0-255，则i＝0，1，2，3，……，255分别对应的像素个数为H(0)，H(1)，H(2)，H(3)，……，H(255)，则

Among them, i represents the gray value of the edge histogram, the value range of i is, for example, an integer from 0 to 255, H(i) represents the number of pixels whose gray value is i in the edge histogram,

Represents the mean of the number of pixels corresponding to each gray value in the edge histogram. For the edge histogram,

Represents the average value of the pixels of the edge histogram. For example, if the value of i is 0-255, the number of pixels corresponding to i=0, 1, 2, 3, ..., 255 is H(0), H(1), H(2), H(3), ..., H(255), then

Referring to FIG. 2 , determine p grayscale values corresponding to the number of pixels in the edge histogram that are smaller than the first sparse value, where p is an integer greater than or equal to 1. The P grayscale values include, for example, grayscale value i=5, grayscale value i=13, grayscale value i=20, and so on. Then, using p gray values as breakpoints, the edge histogram is segmented to obtain M segments.

Referring to FIG. 3 , in an embodiment, the number of pixels corresponding to the p grayscale values may be set to 0. For example, the number of pixels corresponding to the grayscale value i=5 is H(5), the number of pixels corresponding to the grayscale value i=13 is H(13), and the number of pixels corresponding to the grayscale value i=20 is H( 20), for example, set H(5)=0, H(13)=0, H(20)=0, and use gray value i=5, gray value i=13, gray value i=20 respectively The end is used as a breakpoint to divide the edge histogram into M segments. The M segments include, for example, the 1st segment, the 2nd segment, the 3rd segment, ..., the Mth segment.

Similarly, the specific process of segmenting the non-edge histogram to obtain N segments of the non-edge histogram is similar to the processing process of the edge histogram, for example, calculating the second sparse value of the non-edge histogram, the second sparse value using It is used to characterize the degree of deviation of the number of pixels in the non-edge histogram. Then, determine q gray values corresponding to the number of pixels in the non-edge histogram that are less than the second sparse value, where q is an integer greater than or equal to 1, and use the q gray values as breakpoints to classify the non-edge histogram. The N fragments obtained by segment processing. The specific process is not repeated here.

After the M segments of the edge histogram are obtained, the M segments are processed respectively to obtain the processed edge histogram. The specific process is described with reference to the following Figures 4 to 5 . In addition, the N segments may be processed separately to obtain the processed non-edge histogram, and the specific process is the same as or similar to the process of processing the M segments, which will not be repeated here. Finally, the processed edge histogram and the processed non-edge histogram are fused to obtain a fused histogram.

The specific process of processing the M segments to obtain the processed edge histogram will be described below with reference to FIG. 4 to FIG. 5 .

FIG. 4 schematically shows a schematic diagram of performing shift processing on M segments according to an embodiment of the present disclosure. FIG. 5 schematically shows a schematic diagram of shifting grayscale values in each of the M segments according to an embodiment of the present disclosure.

As shown in FIG. 4 , the process of processing the M segments includes, for example, first determining the segment shift distance of each segment in the M segments, and obtaining the M segment shift distances. For example, according to the number of pixels in each of the M segments, the segment number M of the edge histogram, and the total number of pixels of the edge histogram, the segment shift distance of each segment of the M segments is calculated. Specifically, the segment shift distance of each segment in the M segments is, for example, as shown in formula (6).

表示边缘直方图的像素总个数(即M个片段的像素总个数)。Among them, j represents the segment, M represents the total number of segments in the edge histogram, D(j) represents the segment shift distance of the jth segment, x(j) represents the number of pixels contained in the jth segment,

Indicates the total number of pixels in the edge histogram (that is, the total number of pixels in M segments).

After the segment shift distances of each of the M segments are obtained, the M segments are respectively shifted based on the M segment shift distances. That is, each of the M segments is remapped in order to move the grayscale values in each segment from a low grayscale value of the image to a high grayscale value of the image. It can be understood that the greater the number of pixels contained in each segment, the farther the segment is remapped (shifted).

As shown in FIG. 4 , for example, first determine the segment shift distance of the first segment among the M segments as D(1), the segment shift distance of the second segment as D(2), and the segment shift distance of the third segment as D(2). The shift distance is D(3) and so on. Then, the 1st segment, the 2nd segment, the 3rd segment, etc. are shifted in the direction of the higher gray value. FIG. 4 only schematically shows the process of translating the first segment according to the segment shift distance D(1). It can be understood that the shifting process of the second segment, the third segment, ..., the M-th segment is the same as or similar to the shifting process of the first segment, and details are not described herein again.

As shown in FIG. 5 , after each segment in the M segments is shifted according to the corresponding segment shift distance, processing of each segment in the M segments is continued. For example, each of the M segments is sequentially determined as the first segment, the first segment includes m grayscale values, and each grayscale value in the m grayscale values has a corresponding number of pixels, where m is greater than An integer equal to 1.

According to the embodiment of the present disclosure, for example, the gray value shift distance of each of the m gray values in the first segment may be determined to obtain m gray value shift distances. For example, according to the number of pixels of each gray value in the m gray values, the number m of gray values of the first segment, and the total number of pixels of the first segment, each of the m gray values is calculated. Gray value shift distance for gray values. Specifically, the gray value shift distance of each gray value in the m gray values is, for example, as shown in formula (7):

Among them, m represents the width of the first segment (that is, the number of grayscale values of the first segment), k=1, 2, ..., m, k represents the kth grayscale value among the m grayscale values, and L (k) represents the transformation intensity of the kth gray value (that is, the gray value shift distance of the kth gray value), H(k) represents the number of pixels corresponding to the kth gray value, x(j ) represents the number of pixels included in the jth segment (see formula (6)), where x(j) represents the total number of pixels in the first segment.

As shown in FIG. 5 , for example, the first segment among the M segments is determined as the first segment, and the first segment includes, for example, the first gray value, the second gray value, . . . , the kth Gray value, ..., mth gray value. The grayscale value shift distances corresponding to the first grayscale value, the second grayscale value, ..., the kth grayscale value, ..., the mth grayscale value, respectively, are, for example, L(1), L(2), ..., L(k), ..., L(m), and then shift each gray value of the m gray values according to the corresponding gray value shift distance to the gray value of the higher gray value. The direction is shifted.

Similarly, the second segment, the third segment, . . . , the M-th segment among the M segments can be sequentially determined as the first segment, and for each grayscale of the multiple grayscale values in the first segment The process of shifting the value is the same as or similar to the process of shifting the m grayscale values in the first segment, and details are not repeated here. The processed edge histogram is obtained by performing shift processing on a plurality of segments included in each of the M segments.

In the embodiment of the present disclosure, by performing remapping (shifting) processing on multiple segments of the edge histogram, the edge histogram is processed by taking each segment as a whole, thereby enhancing the contrast between different segments, which is reflected in the enhanced The contrast of different parts in the original image is improved, so that the overall brightness of the original image is improved. Secondly, in order to obtain a clearer image, the embodiment of the present disclosure also performs subdivision transformation on the gray value inside each segment to enhance the contrast of the image.

According to an embodiment of the present disclosure, the process of shifting the non-edge histogram may include processing N segments respectively to obtain the processed non-edge histogram. The specific process is the same as or similar to the process of shifting the M segments of the edge histogram.

For example, the segment shift distance of each of the N segments is determined to obtain the N segment shift distances. That is, according to the number of pixels in each of the N segments, the segment number N of the edge histogram, and the total number of pixels of the edge histogram, the segment shift distance of each segment in the N segments is calculated. Then, the N segments are respectively shifted based on the N segment shift distances.

Thereafter, each of the N segments is sequentially determined as the second segment, wherein the second segment includes n grayscale values, and each grayscale value in the n grayscale values has a corresponding number of pixels. , where n is an integer greater than or equal to 1. The gray value shift distance of each gray value in the n gray values is determined, and the n gray value shift distances are obtained.

For example, according to the number of pixels of each gray value in the n gray values, the number n of gray values of the first segment, and the total number of pixels of the first segment, each of the n gray values is calculated. Gray value shift distance for gray values.

Finally, the n gray values are respectively shifted based on the n gray value shift distances, and the processed non-edge histogram is obtained. For the specific process, reference may be made to the process of shifting the M segments of the edge histogram, which will not be repeated here.

After the edge histogram is shifted to obtain the processed edge histogram and the non-edge histogram is shifted to obtain the processed non-edge histogram, the processed edge histogram and the processed non-edge histogram are fused, Get the fusion histogram. Then, the following operation S150 may be continued.

In operation S150, the original histogram is processed based on the fusion histogram to obtain a processed histogram, so as to obtain a processed image according to the processed histogram, so that the contrast of the processed image is higher than that of the original image.

For example, determine the cumulative distribution function of the fused histogram and determine the cumulative distribution function of the original histogram. Then, based on the cumulative distribution function of the fusion histogram and the cumulative distribution function of the original histogram, the histogram specification mapping is performed to obtain the gray value change relationship. Wherein, the gray value variation relationship includes, for example, the enhanced gray value corresponding to each gray value in the original histogram. Finally, based on the change relationship of gray value, each gray value in the original histogram is moved to the corresponding enhanced gray value, and the processed histogram is obtained.

For example, the calculation process of the histogram specification mapping is shown in Equation (8) and Equation (9).

C _input (i)=C _desired (s) (8)

Among them, i represents the gray value of the original histogram, and C _input (i) represents the cumulative distribution function of the original histogram. s represents the gray value of the fusion histogram, and C _desired (s) represents the cumulative distribution function of the fusion histogram. Wherein, s may also represent an enhanced gray value, for example, and in the embodiment of the present disclosure, each gray value in the original histogram may be moved to a corresponding enhanced gray value to obtain a processed histogram.

For example, assuming that the number of pixels corresponding to the grayscale values i=1, 2, and 3 in the original histogram are H(1), H(2), and H(3), respectively, the calculated enhanced grayscale values s are, for example, respectively For s=5, 7, 11. Then, processing the original histogram to obtain the final processed histogram is, for example, specifically: moving the gray value of i=1 in the original histogram to the gray value of 5, so that the gray value of 5 in the processed histogram corresponds to The number of pixels is H(1). Move the gray value i=2 in the original histogram to the gray value of 7, so that the number of pixels corresponding to the gray value 7 in the processed histogram is H(2). Move the gray value i=3 in the original histogram to the gray value of 11, so that the number of pixels corresponding to the gray value of 11 in the processed histogram is H(3). Then, a processed image is obtained according to the processed histogram, so that the contrast of the processed image is higher than that of the original image, thereby realizing the enhancement effect of the image.

The embodiment of the present disclosure obtains an edge image and a non-edge image by splitting the original image, and performs segmentation processing and shift processing on the edge image and the non-edge image respectively to obtain a processed edge histogram and a processed non-edge histogram. Then, the processed edge histogram and the processed non-edge histogram are fused to obtain a fusion histogram, and then histogram specification mapping is performed based on the fusion histogram and the original histogram to obtain an enhanced original image. It can be understood that, by processing the medical image through the image processing method of the embodiment of the present disclosure, the exposure of the medical image is improved, the contrast between light and dark is more delicate, and the details in the darker part of the image are richer, and there will be no excessive enhancement and no extra noise. This greatly improves the image quality, making it easier for medical workers to observe and judge the condition through medical images.

Another aspect of the present disclosure provides an electronic device including: one or more processors; a memory for storing one or more programs, wherein when the one or more programs are executed by the one or more processors , causing one or more processors to perform the methods described in FIGS. 1-5 .

FIG. 6 schematically shows a block diagram of an image processing apparatus according to an embodiment of the present disclosure.

As shown in FIG. 6 , the image processing apparatus 600 includes an acquisition module 610 , a first processing module 620 , a second processing module 630 , a third processing module 640 and a fourth processing module 650 .

The acquisition module 610 may be used to acquire an original image, wherein the original image includes an original histogram. According to an embodiment of the present disclosure, the obtaining module 610 may, for example, perform the operation S110 described above with reference to FIG. 1 , which will not be repeated here.

The first processing module 620 may be used to process the original image to obtain an edge image and a non-edge image. According to an embodiment of the present disclosure, the first processing module 620 may, for example, perform the operation S120 described above with reference to FIG. 1 , which will not be repeated here.

The second processing module 630 may be configured to process the edge image and the non-edge image respectively to obtain the edge histogram of the edge image and the non-edge histogram of the non-edge image. According to an embodiment of the present disclosure, the second processing module 630 may, for example, perform the operation S130 described above with reference to FIG. 1 , which will not be repeated here.

The third processing module 640 may be configured to process the edge histogram and the non-edge histogram to obtain a fusion histogram. According to an embodiment of the present disclosure, the third processing module 640 may, for example, perform the operation S140 described above with reference to FIG. 1 , which will not be repeated here.

The fourth processing module 650 may be configured to process the original histogram based on the fusion histogram to obtain a processed histogram to obtain a processed image from the processed histogram, wherein the contrast of the processed image is higher than that of the original image. According to an embodiment of the present disclosure, the fourth processing module 650 may, for example, perform the operation S150 described above with reference to FIG. 1 , which will not be repeated here.

Any of the modules, sub-modules, units, sub-units, or at least part of the functions of any of them according to embodiments of the present disclosure may be implemented in one module. Any one or more of the modules, sub-modules, units, and sub-units according to the embodiments of the present disclosure may be divided into multiple modules for implementation. Any one or more of the modules, sub-modules, units, sub-units according to embodiments of the present disclosure may be implemented at least in part as hardware circuits, such as field programmable gate arrays (FPGA), programmable logic arrays (PLA), A system on a chip, a system on a substrate, a system on a package, an application specific integrated circuit (ASIC), or any other reasonable means of hardware or firmware that integrates or packages circuits, or can be implemented in software, hardware, and firmware Any one of these implementations or an appropriate combination of any of them is implemented. Alternatively, one or more of the modules, sub-modules, units, and sub-units according to embodiments of the present disclosure may be implemented at least in part as computer program modules that, when executed, may perform corresponding functions.

For example, any number of the acquisition module 610, the first processing module 620, the second processing module 630, the third processing module 640, and the fourth processing module 650 may be combined in one module for implementation, or any one of the modules may be implemented by Split into multiple modules. Alternatively, at least part of the functionality of one or more of these modules may be combined with at least part of the functionality of other modules and implemented in one module. According to an embodiment of the present disclosure, at least one of the acquisition module 610 , the first processing module 620 , the second processing module 630 , the third processing module 640 , and the fourth processing module 650 may be implemented at least partially as a hardware circuit, such as an on-site Programmable Gate Array (FPGA), Programmable Logic Array (PLA), System-on-Chip, System-on-Substrate, System-on-Package, Application-Specific Integrated Circuit (ASIC), or any other reasonable It can be realized by hardware or firmware, or by any one of the three implementation modes of software, hardware and firmware, or by any appropriate combination of any of them. Alternatively, at least one of the acquisition module 610, the first processing module 620, the second processing module 630, the third processing module 640, and the fourth processing module 650 may be implemented at least partially as a computer program module when the computer program module is At runtime, the corresponding function can be executed.

FIG. 7 schematically shows a block diagram of a computer system for implementing image processing according to an embodiment of the present disclosure. The computer system shown in FIG. 7 is only an example, and should not impose any limitation on the function and scope of use of the embodiments of the present disclosure.

As shown in FIG. 7 , a computer system 700 for implementing image processing includes a processor 701 and a computer-readable storage medium 702 . The system 700 may perform methods according to embodiments of the present disclosure.

Specifically, the processor 701 may include, for example, a general-purpose microprocessor, an instruction set processor and/or a related chipset and/or a special-purpose microprocessor (eg, an application specific integrated circuit (ASIC)), and the like. The processor 701 may also include on-board memory for caching purposes. The processor 701 may be a single processing unit or multiple processing units for performing different actions of the method flow according to the embodiment of the present disclosure.

Computer-readable storage medium 702, for example, can be any medium that can contain, store, communicate, propagate, or transmit instructions. For example, a readable storage medium may include, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, device, or propagation medium. Specific examples of readable storage media include: magnetic storage devices, such as magnetic tapes or hard disks (HDDs); optical storage devices, such as compact disks (CD-ROMs); memories, such as random access memory (RAM) or flash memory; and/or wired /Wireless communication link.

The computer-readable storage medium 702 may include a computer program 703, which may include code/computer-executable instructions that, when executed by the processor 701, cause the processor 701 to perform methods according to embodiments of the present disclosure or any variation thereof.

The computer program 703 may be configured with computer program code comprising, for example, computer program modules. For example, in an example embodiment, the code in computer program 703 may include one or more program modules, eg, including 703A, module 703B, . . . It should be noted that the division method and number of modules are not fixed, and those skilled in the art can use appropriate program modules or combination of program modules according to the actual situation. When these combination of program modules are executed by the processor 701, the processor 701 can A method according to an embodiment of the present disclosure or any variation thereof is performed.

According to an embodiment of the present disclosure, at least one of the acquisition module 610, the first processing module 620, the second processing module 630, the third processing module 640, and the fourth processing module 650 may be implemented as a computer program module described with reference to FIG. 7, When executed by the processor 701, it can implement the corresponding operations described above.

The present disclosure also provides a computer-readable medium. The computer-readable medium may be included in the device/device/system described in the above embodiments; it may also exist alone without being assembled into the device/device/system. in the system. The above-mentioned computer-readable medium carries one or more programs, and when the above-mentioned one or more programs are executed, the above image processing method is realized.

According to an embodiment of the present disclosure, the computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or a combination of any of the above. More specific examples of computer readable storage media may include, but are not limited to, electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable Programmable read only memory (EPROM or flash memory), fiber optics, portable compact disk read only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing. In this disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present disclosure, however, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code therein. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device . Program code embodied on a computer readable medium may be transmitted using any suitable medium including, but not limited to, wireless, wireline, optical fiber cable, radio frequency signals, etc., or any suitable combination of the foregoing.

The flowchart and block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code that contains one or more logical functions for implementing the specified functions executable instructions. It should also be noted that, in some alternative implementations, the functions noted in the blocks may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It is also noted that each block in the block diagrams or flowchart illustrations, and combinations of blocks in the block diagrams or flowchart illustrations, can be implemented by special purpose hardware-based systems that perform the specified functions or operations, or by special purpose hardware-based systems that perform the specified functions or operations. A combination of hardware and computer instructions is implemented.

Those skilled in the art will appreciate that various combinations and/or combinations of features recited in various embodiments and/or claims of the present disclosure are possible, even if such combinations or combinations are not expressly recited in the present disclosure. In particular, various combinations and/or combinations of the features recited in the various embodiments of the present disclosure and/or in the claims may be made without departing from the spirit and teachings of the present disclosure. All such combinations and/or combinations fall within the scope of this disclosure.

Although the present disclosure has been shown and described with reference to specific exemplary embodiments of the present disclosure, those skilled in the art will appreciate that, without departing from the spirit and scope of the present disclosure as defined by the appended claims and their equivalents, Various changes in form and detail have been made in the present disclosure. Therefore, the scope of the present disclosure should not be limited to the above-described embodiments, but should be determined not only by the appended claims, but also by their equivalents.

Claims (13)

1. An image processing method comprising:

acquiring an original image, wherein the original image comprises an original histogram;

processing the original image to obtain an edge image and a non-edge image;

processing the edge image and the non-edge image respectively to obtain an edge histogram of the edge image and a non-edge histogram of the non-edge image;

processing the edge histogram and the non-edge histogram to obtain a fused histogram; and

processing the original histogram based on the fused histogram to obtain a processed histogram, so as to obtain a processed image according to the processed histogram, wherein the contrast of the processed image is higher than that of the original image.

2. The method of claim 1, wherein said processing said edge histogram and said non-edge histogram to obtain a fused histogram comprises:

respectively carrying out segmentation processing on the edge histogram and the non-edge histogram to obtain M segments of the edge histogram and N segments of the non-edge histogram, wherein M is an integer larger than 1, and N is an integer larger than 1;

processing the M segments respectively to obtain processed edge histograms;

processing the N segments respectively to obtain processed non-edge histograms; and

and fusing the processed edge histogram and the processed non-edge histogram to obtain the fused histogram.

3. The method of claim 2, wherein said processing the M segments separately to obtain processed edge histograms comprises:

determining the segment shift distance of each of the M segments to obtain M segment shift distances;

respectively carrying out shift processing on the M segments based on the M segment shift distances;

sequentially determining each of the M segments as a first segment, wherein the first segment comprises M gray values, each gray value of the M gray values has a corresponding pixel number, and M is an integer greater than or equal to 1;

determining the gray value shift distance of each gray value in the m gray values to obtain m gray value shift distances; and

and respectively carrying out shift processing on the m gray values based on the shift distances of the m gray values to obtain the processed edge histogram.

4. The method of claim 2 or 3, wherein the processing the N segments to obtain processed non-edge histograms respectively comprises:

determining the segment shift distance of each segment in the N segments to obtain N segment shift distances;

shifting the N segments based on the N segment shifting distances respectively;

sequentially determining each of the N segments as a second segment, wherein the second segment comprises N gray values, each gray value of the N gray values has a corresponding pixel number, and N is an integer greater than or equal to 1;

determining a gray value shift distance of each gray value in the n gray values to obtain n gray value shift distances; and

and respectively carrying out shift processing on the n gray values based on the shift distances of the n gray values to obtain the processed non-edge histogram.

5. The method of claim 3, wherein:

the determining a segment shift distance for each of the M segments comprises: calculating the segment shift distance of each segment in the M segments according to the number of pixels in each segment in the M segments, the number M of the segments of the edge histogram and the total number of pixels of the edge histogram;

the determining a gray value shift distance for each of the m gray values comprises: and calculating the gray value shift distance of each gray value in the m gray values according to the number of pixels of each gray value in the m gray values, the number m of the gray values of the first segment and the total number of pixels of the first segment.

6. The method of claim 4, wherein:

the determining a segment shift distance for each of the N segments comprises: calculating the segment shift distance of each segment in the N segments according to the number of pixels in each segment in the N segments, the number N of the segments of the edge histogram and the total number of pixels of the edge histogram;

the determining a gray value shift distance for each of the n gray values comprises: and calculating the gray value shift distance of each gray value in the n gray values according to the number of pixels of each gray value in the n gray values, the number n of the gray values of the first segment and the total number of pixels of the first segment.

7. The method of claim 2, wherein the segmenting the edge histogram and the non-edge histogram to obtain M segments of the edge histogram and N segments of the non-edge histogram comprises:

calculating a first sparse value of the edge histogram and a second sparse value of the non-edge histogram, wherein the first sparse value is used for representing the deviation degree of each pixel number in the edge histogram, and the second sparse value is used for representing the deviation degree of each pixel number in the non-edge histogram;

determining p gray values corresponding to the situation that the number of pixels in the edge histogram is smaller than the first sparse value, wherein p is an integer larger than or equal to 1;

determining q gray values corresponding to the situation that the number of pixels in the non-edge histogram is smaller than the second sparse value, wherein q is an integer larger than or equal to 1;

taking the p gray values as breakpoints, and carrying out segmentation processing on the edge histogram to obtain M segments; and

and taking the q gray values as break points, and carrying out segmentation processing on the non-edge histogram to obtain N segments.

8. The method of claim 1, wherein said processing said original histogram based on said fused histogram resulting in a processed histogram comprises:

determining a cumulative distribution function of the fused histogram;

determining a cumulative distribution function of the original histogram;

calculating the cumulative distribution function of the fused histogram and the cumulative distribution function of the original histogram to obtain a gray value change relation, wherein the gray value change relation comprises enhanced gray values corresponding to all gray values in the original histogram; and

and moving each gray value in the original histogram to a corresponding enhanced gray value based on the gray value change relation to obtain a processed histogram.

9. The method of claim 1, wherein the processing the original image to obtain an edge image and a non-edge image comprises:

calculating a gradient value of each pixel in the original image;

determining pixels with gradient values larger than a preset gradient value as pixels in the edge image; and

and determining the pixels with the gradient values smaller than or equal to the preset gradient values as the pixels in the non-edge image.

10. The method of claim 1, further comprising:

before processing the original image to obtain an edge image and a non-edge image, filtering the original image by using a Gaussian filtering mode so as to remove at least part of noise information in the original image.

11. An image processing apparatus comprising:

the device comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring an original image, and the original image comprises an original histogram;

the first processing module is used for processing the original image to obtain an edge image and a non-edge image;

the second processing module is used for respectively processing the edge image and the non-edge image to obtain an edge histogram of the edge image and a non-edge histogram of the non-edge image;

the third processing module is used for processing the edge histogram and the non-edge histogram to obtain a fused histogram; and

and the fourth processing module is used for processing the original histogram based on the fused histogram to obtain a processed histogram so as to obtain a processed image according to the processed histogram, wherein the contrast of the processed image is higher than that of the original image.

12. An electronic device, comprising:

one or more processors;

a storage device for storing one or more programs,

wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to perform the method of any of claims 1-10.

13. A computer readable storage medium having stored thereon executable instructions which, when executed by a processor, cause the processor to perform the method of any one of claims 1 to 10.

Images