CN113506231B

CN113506231B - Processing method and device for pixels in image, medium and electronic equipment

Info

Publication number: CN113506231B
Application number: CN202110886779.1A
Authority: CN
Inventors: 王亚领; 肖杨; 钟能; 刘设伟
Original assignee: Taikang Insurance Group Co Ltd; Taikang Online Property Insurance Co Ltd
Current assignee: Taikang Insurance Group Co Ltd; Taikang Online Property Insurance Co Ltd
Priority date: 2021-08-03
Filing date: 2021-08-03
Publication date: 2023-06-27
Anticipated expiration: 2041-08-03
Also published as: CN113506231A

Abstract

The embodiment of the disclosure provides a processing method for pixels in an image, a processing device for pixels in an image, a computer readable medium and electronic equipment, and relates to the technical field of image processing, wherein the method comprises the following steps: determining a plurality of target pixels in a preset pixel value range in a target image; performing mean filtering processing on the target image to obtain a first reference image; replacing each target pixel in the target image with a pixel consistent with each target pixel in the first reference image to obtain a second reference image; and sequentially performing pixel value nonlinear transformation processing, gray enhancement processing and exponential transformation processing on the second reference image to obtain an image processing result. Therefore, by implementing the technical scheme, the processing result suitable for automatic content identification can be obtained through processing the pixels of the image, so that the extraction efficiency and the extraction precision of the content with specific colors in the image can be improved.

Description

Processing method and device for pixels in image, medium and electronic equipment

Technical Field

The present disclosure relates to the field of image processing technology, and in particular, to a processing method for a pixel in an image, a processing device for a pixel in an image, a computer readable medium, and an electronic device.

Background

The image containing the seal is often a bill photo, and the bill photo is taken as a reserved evidence image and can be generally applied to the way of reimbursement and the like. For a ticket photograph provided by a user, a verification person typically needs to manually input the stamp content in the image to a corresponding system or platform for verification and record. However, manual input often suffers from inefficiency.

It should be noted that the information disclosed in the above background section is only for enhancing understanding of the background of the present disclosure and thus may include information that does not constitute prior art known to those of ordinary skill in the art.

Disclosure of Invention

An object of an embodiment of the present disclosure is to provide a processing method for a pixel in an image, a processing device for a pixel in an image, a computer readable medium, and an electronic device, which can obtain a processing result suitable for performing automatic content recognition by processing a pixel of an image, thereby being beneficial to improving extraction efficiency and extraction accuracy of content for a specific color in an image.

A first aspect of an embodiment of the present disclosure provides a processing method for a pixel in an image, the method including:

determining a plurality of target pixels in a preset pixel value range in a target image;

Performing mean filtering processing on the target image to obtain a first reference image;

replacing each target pixel in the target image with a pixel consistent with each target pixel in the first reference image to obtain a second reference image;

and sequentially performing pixel value nonlinear transformation processing, gray enhancement processing and exponential transformation processing on the second reference image to obtain an image processing result.

In an exemplary embodiment of the present disclosure, a pixel value nonlinear transformation process, a gray enhancement process, and an exponential transformation process are sequentially performed on a second reference image to obtain an image processing result, including:

performing nonlinear transformation processing on pixel values of all pixels in the second reference image according to a preset reduction rule to obtain a third reference image of the single pixel channel;

carrying out gray enhancement processing on all pixels in the third reference image according to a preset transformation relation to obtain a fourth reference image;

and carrying out pixel differentiation processing on all pixels in the fourth reference image according to the preset conversion coefficient to obtain an image processing result.

In an exemplary embodiment of the present disclosure, performing a nonlinear transformation process on pixel values of all pixels in a second reference image according to a preset reduction rule to obtain a third reference image of a single pixel channel, including:

Three-channel pixel value transformation is carried out on all pixels in the second reference image, and the maximum value in the transformation result is determined, so that the maximum value corresponding to each pixel in the second reference image is obtained;

determining a final transformation result of each pixel in the second reference image according to the transformation result and the maximum value of each pixel in the second reference image;

and replacing the corresponding pixels in the second reference image with the final transformation result until all the pixels in the second reference image are replaced, so as to obtain a third reference image of the single pixel channel.

In an exemplary embodiment of the present disclosure, performing gray enhancement processing on all pixels in a third reference image according to a preset transformation relationship to obtain a fourth reference image, including:

performing histogram equalization on the third reference image according to a preset transformation relationship to realize gray enhancement on the third reference image and obtain a fourth reference image; wherein, all pixels in the fourth reference image accord with the preset gray value range.

In an exemplary embodiment of the present disclosure, performing pixel differentiation processing on all pixels in a fourth reference image according to a preset transform coefficient to obtain an image processing result, including:

Determining a preset transformation coefficient as an index of each pixel point in the fourth reference image;

and performing index transformation on all pixels in the fourth reference image according to the index to obtain an image processing result.

In an exemplary embodiment of the present disclosure, replacing each target pixel in the target image with a pixel in the first reference image that coincides with each target pixel location, resulting in a second reference image, includes:

determining a plurality of reference pixels in the same position as the plurality of target pixels from a first reference image; wherein, the plurality of reference pixels and the plurality of target pixels are in one-to-one correspondence;

and replacing a plurality of target pixels in the target image with a plurality of reference pixels based on a one-to-one correspondence, so as to obtain a second reference image.

In an exemplary embodiment of the present disclosure, the preset pixel value range includes a red channel value range, a green channel value range, and a blue channel value range, and determining a plurality of target pixels in the preset pixel value range in the target image includes:

and traversing the red pixel value, the green pixel value and the blue pixel value of each pixel in the target image to determine a plurality of target pixels at least conforming to at least one of the red channel value range, the green channel value range and the blue channel value range.

According to a second aspect of embodiments of the present disclosure, there is provided a processing apparatus for a pixel in an image, including:

a pixel selection unit, configured to determine a plurality of target pixels in a preset pixel value range in a target image;

the average filtering unit is used for carrying out average filtering processing on the target image to obtain a first reference image;

the pixel replacing unit is used for replacing each target pixel in the target image with a pixel consistent with each target pixel in the first reference image to obtain a second reference image;

and the pixel processing unit is used for sequentially carrying out pixel value nonlinear transformation processing, gray enhancement processing and exponential transformation processing on the second reference image to obtain an image processing result.

In an exemplary embodiment of the present disclosure, a pixel processing unit sequentially performs a pixel value nonlinear transformation process, a gray enhancement process, and an exponential transformation process on a second reference image, to obtain an image processing result, including:

In an exemplary embodiment of the present disclosure, a pixel processing unit performs a nonlinear transformation process on pixel values of all pixels in a second reference image according to a preset reduction rule, to obtain a third reference image of a single pixel channel, including:

In an exemplary embodiment of the present disclosure, the pixel processing unit performs gray enhancement processing on all pixels in the third reference image according to a preset transformation relationship to obtain a fourth reference image, including:

In an exemplary embodiment of the present disclosure, a pixel processing unit performs pixel differentiation processing on all pixels in a fourth reference image according to a preset transform coefficient to obtain an image processing result, including:

In an exemplary embodiment of the present disclosure, a pixel replacement unit replaces each target pixel in a target image with a pixel in a first reference image that coincides with each target pixel in position, resulting in a second reference image, including:

In an exemplary embodiment of the present disclosure, the preset pixel value range includes a red channel value range, a green channel value range, and a blue channel value range, and the pixel selection unit determines a plurality of target pixels in the preset pixel value range in the target image, including:

According to a third aspect of embodiments of the present disclosure, there is provided a computer readable medium having stored thereon a computer program which, when executed by a processor, implements a processing method for pixels in an image as in the first aspect of the above embodiments.

According to a fourth aspect of embodiments of the present disclosure, there is provided an electronic device, comprising: one or more processors; and storage means for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to implement the processing method for pixels in an image as in the first aspect of the embodiments described above.

According to a fifth aspect of the present application, there is provided a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The computer instructions are read from the computer-readable storage medium by a processor of a computer device, and executed by the processor, cause the computer device to perform the methods provided in the various alternative implementations described above.

The technical scheme provided by the embodiment of the disclosure can comprise the following beneficial effects:

the technical solutions provided in some embodiments of the present disclosure specifically include: determining a plurality of target pixels in a preset pixel value range in a target image; performing mean filtering processing on the target image to obtain a first reference image; replacing each target pixel in the target image with a pixel consistent with each target pixel in the first reference image to obtain a second reference image; and sequentially performing pixel value nonlinear transformation processing, gray enhancement processing and exponential transformation processing on the second reference image to obtain an image processing result. According to the embodiment of the disclosure, on one hand, the processing result suitable for content identification can be output through processing the target image, so that automatic identification of the content with the specific color in the image can be conveniently realized, and the extraction efficiency of the content with the specific color in the image can be improved. On the other hand, the required image processing result can be determined through specific pixel replacement of the image, nonlinear transformation processing, gray enhancement processing and exponential transformation processing of the pixel value of the image, and the identification precision can be improved for the content identification of the specific color of the image processing result, so that the extraction precision of the content of the specific color can be improved.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the principles of the disclosure. It will be apparent to those of ordinary skill in the art that the drawings in the following description are merely examples of the disclosure and that other drawings may be derived from them without undue effort.

FIG. 1 schematically illustrates a schematic diagram of an exemplary system architecture for a processing method for pixels in an image and a processing apparatus for pixels in an image to which embodiments of the present disclosure may be applied;

FIG. 2 schematically illustrates a structural schematic of a computer system suitable for use in implementing electronic devices of embodiments of the present disclosure;

FIG. 3 schematically illustrates a flow chart of a processing method for pixels in an image, according to one embodiment of the disclosure;

FIG. 4 schematically illustrates a step-wise processing result schematic a of content of a specific color in a target image according to one embodiment of the present disclosure;

FIG. 5 schematically illustrates a step-wise processing result schematic b of content of a specific color in a target image according to one embodiment of the present disclosure;

FIG. 6 schematically illustrates a flow chart of a processing method for pixels in an image, according to one embodiment of the disclosure;

fig. 7 schematically illustrates a block diagram of a processing apparatus for pixels in an image in accordance with one embodiment of the present disclosure.

Detailed Description

Example embodiments will now be described more fully with reference to the accompanying drawings. However, the exemplary embodiments may be embodied in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the present disclosure. One skilled in the relevant art will recognize, however, that the aspects of the disclosure may be practiced without one or more of the specific details, or with other methods, components, devices, steps, etc. In other instances, well-known technical solutions have not been shown or described in detail to avoid obscuring aspects of the present disclosure.

Furthermore, the drawings are merely schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus a repetitive description thereof will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in software or in one or more hardware modules or integrated circuits or in different networks and/or processor devices and/or microcontroller devices.

Fig. 1 shows a schematic diagram of a system architecture of an exemplary application environment for a processing method for pixels in an image and a processing apparatus for pixels in an image, to which embodiments of the present disclosure may be applied.

As shown in fig. 1, the system architecture 100 may include one or more of the

terminal devices

101, 102, 103, a network 104, and a server 105. The network 104 is used as a medium to provide communication links between the

terminal devices

101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others. The

terminal devices

101, 102, 103 may be various electronic devices with display screens including, but not limited to, desktop computers, portable computers, smart phones, tablet computers, and the like. It should be understood that the number of terminal devices, networks and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation. For example, the server 105 may be a server cluster formed by a plurality of servers. Wherein the server 105 is configured to perform: determining a plurality of target pixels in a preset pixel value range in a target image; performing mean filtering processing on the target image to obtain a first reference image; replacing each target pixel in the target image with a pixel consistent with each target pixel in the first reference image to obtain a second reference image; and sequentially performing pixel value nonlinear transformation processing, gray enhancement processing and exponential transformation processing on the second reference image to obtain an image processing result.

Fig. 2 shows a schematic diagram of a computer system suitable for use in implementing embodiments of the present disclosure.

It should be noted that the computer system 200 of the electronic device shown in fig. 2 is only an example, and should not impose any limitation on the functions and the application scope of the embodiments of the present disclosure.

As shown in fig. 2, the computer system 200 includes a Central Processing Unit (CPU) 201, which can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 202 or a program loaded from a storage section 208 into a Random Access Memory (RAM) 203. In (RAM) 203, various programs and data required for system operation are also stored. The (CPU) 201, (ROM) 202, and (RAM) 203 are connected to each other through a bus 204. An input/output (I/O) interface 205 is also connected to bus 204.

The following components are connected to the (I/O) interface 205: an input section 206 including a keyboard, a mouse, and the like; an output portion 207 including a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker, and the like; a storage section 208 including a hard disk or the like; and a communication section 209 including a network interface card such as a LAN card, a modem, and the like. The communication section 209 performs communication processing via a network such as the internet. The drive 210 is also connected to the (I/O) interface 205 as needed. A removable medium 211 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is installed on the drive 210 as needed, so that a computer program read therefrom is installed into the storage section 208 as needed.

In particular, according to embodiments of the present disclosure, the processes described below with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method shown in the flowcharts. In such an embodiment, the computer program may be downloaded and installed from a network via the communication portion 209, and/or installed from the removable medium 211. The computer program, when executed by a Central Processing Unit (CPU) 201, performs the various functions defined in the methods and apparatus of the present application.

It should be noted that the computer readable medium shown in the present disclosure may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this disclosure, a computer-readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present disclosure, however, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.

The flowcharts 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, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block 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 will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units involved in the embodiments of the present disclosure may be implemented by means of software, or may be implemented by means of hardware, and the described units may also be provided in a processor. Wherein the names of the units do not constitute a limitation of the units themselves in some cases.

As another aspect, the present application also provides a computer-readable medium that may be contained in the electronic device described in the above embodiment; or may exist alone without being incorporated into the electronic device. The computer-readable medium carries one or more programs which, when executed by one of the electronic devices, cause the electronic device to implement the methods described in the embodiments below. For example, the electronic device may implement the steps shown in fig. 3, and so on.

The present exemplary embodiment provides a processing method for a pixel in an image, which referring to fig. 3, may include the following steps S310 to S340, specifically:

step S310: a plurality of target pixels in a target image within a preset pixel value range are determined.

Step S320: and carrying out mean filtering processing on the target image to obtain a first reference image.

Step S330: and replacing each target pixel in the target image with a pixel consistent with each target pixel in the first reference image to obtain a second reference image.

Step S340: and sequentially performing pixel value nonlinear transformation processing, gray enhancement processing and exponential transformation processing on the second reference image to obtain an image processing result.

By implementing the processing method for the pixels in the image shown in fig. 3, the processing result suitable for content identification can be output through processing the target image, so that automatic identification of the content with the specific color in the image can be conveniently realized, and the extraction efficiency of the content with the specific color in the image can be further improved. In addition, the required image processing result can be determined through specific pixel replacement of the image, nonlinear transformation processing, gray enhancement processing and exponential transformation processing of the pixel value of the image, and the identification precision can be improved for the content identification of the specific color of the image processing result, so that the extraction precision of the content of the specific color can be improved.

Next, the above steps of the present exemplary embodiment will be described in more detail.

In step S310, a plurality of target pixels in a preset pixel value range in the target image are determined.

Specifically, the target image may be a complete medical checklist image or a partial screenshot of the medical checklist image. The preset pixel value range may be used to define the range of at least one pixel value. In the target image, each pixel may be composed of a plurality of pixel values (e.g., RGB values), for example, pixel a is composed of red 213, green 64, blue 124, and the color of pixel a in the target image may be represented by (red 213, green 64, blue 124).

As an alternative embodiment, the preset pixel value range includes a red channel value range, a green channel value range, and a blue channel value range, and determining a plurality of target pixels in the target image within the preset pixel value range includes: and traversing the red pixel value, the green pixel value and the blue pixel value of each pixel in the target image to determine a plurality of target pixels at least conforming to at least one of the red channel value range, the green channel value range and the blue channel value range.

Specifically, the red channel value range, the green channel value range, and the blue channel value range may be the same or different, which is not limited in the embodiment of the present application. For example, the red channel range is: r (x, y) ε [0, 80]; the value range of the green channel is as follows: g (x, y) e [0, 80]. The range of the blue channel is as follows: b (x, y) ε [0, 80]. Wherein R (x, y), G (x, y), B (x, y) represent RGB values of the pixel point (x, y), respectively.

Specifically, traversing the red pixel value, the green pixel value, and the blue pixel value of each pixel in the target image to determine a plurality of target pixels at least conforming to at least one of a red channel value range, a green channel value range, and a blue channel value range, including: the red pixel value R (x, y) e [0, 80], the green pixel value G (x, y) e [0, 80] and the blue pixel value B (x, y) e [0, 80] of each pixel in the target image are traversed to determine a plurality of target pixels (x, y), (x, y) e D that conform to the red channel value range R (x, y) e [0, 80], the green channel value range G (x, y) e [0, 80] and the blue channel value range B (x, y) e [0, 80], where D is a set that includes all of the target pixels.

It can be seen that, by implementing this alternative embodiment, the accuracy of identifying the target pixel can be improved by defining the red channel value range, the green channel value range, and the blue channel value range, thereby facilitating the automatic extraction of the content of the specific color in the image.

In step S320, the target image is subjected to mean filtering processing, so as to obtain a first reference image.

In particular, mean filtering (i.e., low pass filtering)The method is used for giving the average value in the field to the central element, and further averaging the pixel values in the whole window range based on a linear method, so that the effects of smoothing the image and filtering noise are achieved. An average filter removes irrelevant details in the image, an irrelevant meaning a small pixel area compared to the template of the filter. Based on the above, the average filtering processing is performed on the target image to obtain a first reference image, which includes: determining a pixel value f (x, y) of each pixel (x, y) in the target image, wherein f (x, y) can be calculated by R (x, y), G (x, y) and B (x, y); inputting the pixel value f (x, y) of each pixel into the expression

Determining g (x, y) corresponding to each pixel, wherein the g (x, y) corresponding to each pixel is used for forming a first reference image, and the number of pixels of the first reference image is the same as that of the target image; where s is a set of all pixels in the filter kernel, and M represents the number of pixels in s. For example, if the filter kernel is 5,s, the square area with a side length of 5 centered on (x, y) contains 25 pixels, and m=25.

In step S330, each target pixel in the target image is replaced with a pixel in the first reference image that coincides with each target pixel position, so as to obtain a second reference image.

Specifically, the sizes of the target image, the first reference image, the second reference image, the third reference image, the fourth reference image and the image processing result are the same, the pixel numbers are the same, and the pixel values are different.

As an alternative embodiment, replacing each target pixel in the target image with a pixel in the first reference image, which corresponds to the position of each target pixel, to obtain a second reference image, including: determining a plurality of reference pixels in the same position as the plurality of target pixels from a first reference image; wherein, the plurality of reference pixels and the plurality of target pixels are in one-to-one correspondence; and replacing a plurality of target pixels in the target image with a plurality of reference pixels based on a one-to-one correspondence, so as to obtain a second reference image.

Specifically, determining a plurality of reference pixels at the same position as a plurality of target pixels from a first reference image includes: a plurality of reference pixels at the same position in the first reference image are determined based on the positions of the plurality of target pixels in the target image. Based on this, a plurality of target pixels in the target image are replaced with a plurality of reference pixels based on a one-to-one correspondence, resulting in a second reference image, comprising: the target pixels at the same position are replaced by corresponding reference pixels, so that all the target pixels in the target image can be replaced by corresponding reference pixels.

For example, the target image includes a target pixel a at a position 1, a target pixel b at a position 2, and a target pixel c at a position 3, the first reference image includes a reference pixel a ' at a position 1, a reference pixel b ' at a position 2, and a reference pixel c ' at a position 3, and since the target pixel a and the reference pixel a ' are both at a position 1, the target pixel b and the reference pixel b ' are both at a position 2, and the target pixel c and the reference pixel c ' are both at a position 3, the target pixel a in the target image may be replaced with the reference pixel a ', the target pixel b in the target image may be replaced with the reference pixel b ', and the target pixel c in the target image may be replaced with the reference pixel c '.

It can be seen that implementing this alternative embodiment, by performing the co-located replacement of the specific pixel, the color for the specific pixel in the target image can be deepened, so that the content of the specific color is easily identified, thereby improving the identification accuracy of the content of the specific color.

In step S340, the second reference image is subjected to the pixel value nonlinear conversion process, the gradation enhancement process, and the exponential conversion process in order, to obtain an image processing result.

Specifically, the second reference image is sequentially subjected to the pixel value nonlinear conversion process, the gray enhancement process, and the exponential conversion process, which are not limited in this embodiment.

Optionally, after performing the pixel value nonlinear transformation process, the gray enhancement process, and the exponential transformation process on the second reference image in order, the method may further include: traversing the image processing result through a sliding window algorithm to realize character area identification of the image processing result; performing one-dimensional sliding window movement in a text rectangle of a text region recognition result to divide characters according to character spacing so as to determine text information, wherein each text information can contain one or more characters; and extracting the text information.

As an alternative embodiment, the pixel value nonlinear transformation process, the gray enhancement process and the exponential transformation process are sequentially performed on the second reference image, so as to obtain an image processing result, which includes: performing nonlinear transformation processing on pixel values of all pixels in the second reference image according to a preset reduction rule to obtain a third reference image of the single pixel channel; carrying out gray enhancement processing on all pixels in the third reference image according to a preset transformation relation to obtain a fourth reference image; and carrying out pixel differentiation processing on all pixels in the fourth reference image according to the preset conversion coefficient to obtain an image processing result.

Specifically, a preset reduction rule is used to define an expression for channel reduction to change the three-channel image to a single-channel image. The preset transformation relationship is used for defining an expression for gray scale enhancement to enhance the color contrast in the image. The preset transform coefficients are used to define preset parameters within the pixel-differentiated expression to enhance the differences of a particular color from other colors in a single channel.

It can be seen that implementing this alternative embodiment is capable of achieving enhancement of a specific color in a target image and suppression of other colors by a pixel value nonlinear conversion process, a gradation enhancement process, and an exponential conversion process, thereby contributing to improvement of recognition accuracy of content of the specific color.

As an optional embodiment, performing a nonlinear transformation process on pixel values of all pixels in the second reference image according to a preset reduction rule to obtain a third reference image with a single pixel channel, where the method includes: three-channel pixel value transformation is carried out on all pixels in the second reference image, and the maximum value in the transformation result is determined, so that the maximum value corresponding to each pixel in the second reference image is obtained; determining a final transformation result of each pixel in the second reference image according to the transformation result and the maximum value of each pixel in the second reference image; and replacing the corresponding pixels in the second reference image with the final transformation result until all the pixels in the second reference image are replaced, so as to obtain a third reference image of the single pixel channel.

Specifically, three-way pixel value transformation is performed on all pixels in the second reference image, including: three-way pixel value transformations (i.e., RGB pixel value transformations) are performed on all pixels in the second reference image based on the expressions R '=r/255, G' =g/255, and B '=b/255, thereby obtaining (R', G ', B') to which all pixels in the second reference image correspond, respectively, as a transformation result. Based on the above, determining a maximum value in the transformation result, and obtaining a maximum value corresponding to each pixel in the second reference image, including: the maximum value in the transformation result (R ', G', B ') is determined based on the expression k=max (R', G ', B'). Based on this, determining a final transform result for each pixel in the second reference image from the transform result and the maxima for each pixel in the second reference image, comprising: based on the expression

The transformation result (R ', G ', B ') of each pixel in the second reference image and the corresponding maximum value of each pixel in the second reference image determine the final transformation result I of each pixel in the second reference image.

Therefore, by implementing the alternative embodiment, the consistency of other colors except the specific color in the target image can be realized through the nonlinear transformation processing of the pixel values of all the pixels in the second reference image, so that the problem that the contents of multiple colors are mutually overlapped is solved, and the identification precision of the contents of the specific color is improved.

As an optional embodiment, performing gray enhancement processing on all pixels in the third reference image according to a preset transformation relationship to obtain a fourth reference image, including: performing histogram equalization on the third reference image according to a preset transformation relationship to realize gray enhancement on the third reference image and obtain a fourth reference image; wherein, all pixels in the fourth reference image accord with the preset gray value range.

Specifically, performing histogram equalization on the third reference image according to a preset transformation relationship to realize gray enhancement on the third reference image, so as to obtain a fourth reference image, including: expression s defined according to preset transformation relationship _k ＝T(r _k ) And

k=0, 1,2, l-1. Wherein s is _k Is the gray level of the normalized third reference image, r _k The gray level before the normalization of the third reference image is that N represents the number of pixels in the target image, and the preset gray value range of the fourth reference image obtained after normalization is [0, L-1 ]]. When L takes on 255, r=0 represents black, r=l-1 represents white, and n _i Is of gray level r _i The number of pixels in the third reference image. It should be noted that histogram equalization is a method for enhancing the contrast of an image, and is specifically used for converting the histogram distribution of the image into approximately uniform distribution, so as to enhance the contrast of the image, thus increasing the dynamic range of the gray value difference between pixels, and further achieving the effect of enhancing the overall contrast of the image.

It will be seen that this alternative embodiment is implemented to enable the contrast of the image to be enhanced by the grey scale enhancement process to make the image more sharp so that the text recognition process can more accurately identify the content in the image.

As an optional embodiment, performing pixel differentiation processing on all pixels in the fourth reference image according to a preset transform coefficient to obtain an image processing result, including: determining a preset transformation coefficient as an index of each pixel point in the fourth reference image; and performing index transformation on all pixels in the fourth reference image according to the index to obtain an image processing result.

Specifically, the preset transform coefficient is determined as the fourth parameterThe index of each pixel point in the test image comprises: a preset transform coefficient γ is selected from the set of transform coefficients according to the type of the target image (e.g., medical ticket, shopping ticket, etc.), where γ is a constant (e.g., 1.2) as an index of each pixel point in the fourth reference image. Based on the above, performing exponential transformation on all pixels in the fourth reference image according to the exponent, to obtain an image processing result, including: determining the expression s=r from γ ^γ Where r is the pixel value before exponential transformation and s is the pixel value after exponential transformation; according to s=r ^γ And performing exponential transformation on all pixels in the fourth reference image to obtain an image processing result.

It can be seen that by implementing the alternative embodiment, the color difference between the text and the background can be increased through the pixel differentiation process, so that the recognition accuracy and the recognition efficiency of the content with the specific color in the target image can be improved.

In the claim settlement link of insurance, a customer will upload a plurality of claim settlement image data, wherein the image data will generally include a medical invoice photo, the hospital name in the medical invoice photo is generally important information in the verification process, the hospital name information on the medical invoice photo often exists in a seal and easily forms a gland with other characters in the medical invoice photo, so that the character recognition in a red seal is difficult, and in order to solve the problem, please refer to fig. 4, fig. 4 schematically shows a step-by-step processing result diagram a of specific color content in a target image according to one embodiment of the disclosure. As shown in fig. 4, the step-by-step processing result of the content of the specific color in the target image includes: a target image 410, a first reference image 420, a second reference image 430, a third reference image 440, a fourth reference image 450, and an image processing result 460. Specifically, a plurality of target pixels in a preset pixel value range in the received target image 410 may be determined, and then the average filtering process is performed on the target image 410 to obtain the first reference image 420. Further, each target pixel in the target image 410 may be replaced with a pixel in the first reference image 420 that coincides with each target pixel location, resulting in the second reference image 430. Furthermore, the nonlinear transformation of the pixel values may be performed on all pixels in the second reference image 430 according to a preset reduction rule, so as to obtain a third reference image 440 with a single pixel channel; gray enhancement processing is performed on all pixels in the third reference image 440 according to a preset transformation relationship, so as to obtain a fourth reference image 450; and performing pixel differentiation processing on all pixels in the fourth reference image 450 according to the preset transformation coefficient to obtain an image processing result 460.

As another processing way to solve the above-mentioned problem, referring to fig. 5, fig. 5 schematically shows a step-by-step processing result diagram b of contents of a specific color in a target image according to an embodiment of the present disclosure. As shown in fig. 5, the step-by-step processing result of the content of the specific color in the target image includes: image 510, image 520, image 530. Specifically, the received image 510 may be subjected to histogram equalization according to a preset transformation relationship to implement gray enhancement on the image 510, so as to obtain an image 520. Furthermore, pixel differentiation processing is performed on all pixels in the image 520 according to the preset transform coefficient, so as to obtain an image 530. Processing the target image in this manner is more efficient, but the sharpness and color variance of the image processing result 460 shown in fig. 4 is better than that of the image 530. Based on this, the user may select the step-by-step processing manner of fig. 4 or the step-by-step processing manner of fig. 5 according to the need, which is not limited in the embodiment of the present application.

Referring to fig. 6, fig. 6 schematically illustrates a flow chart of a processing method for pixels in an image according to one embodiment of the disclosure. As shown in fig. 6, the processing method for the pixels in the image may include: step S610 to step S690.

Step S610: and traversing the red pixel value, the green pixel value and the blue pixel value of each pixel in the target image to determine a plurality of target pixels at least conforming to at least one of the red channel value range, the green channel value range and the blue channel value range.

Step S620: and carrying out mean filtering processing on the target image to obtain a first reference image.

Step S630: determining a plurality of reference pixels in the same position as the plurality of target pixels from a first reference image; wherein, the reference pixels and the target pixels are in one-to-one correspondence.

Step S640: and replacing a plurality of target pixels in the target image with a plurality of reference pixels based on a one-to-one correspondence, so as to obtain a second reference image.

Step S650: and carrying out three-channel pixel value transformation on all pixels in the second reference image, and determining the maximum value in the transformation result to obtain the maximum value corresponding to each pixel in the second reference image.

Step S660: and determining the final transformation result of each pixel in the second reference image according to the transformation result and the maximum value of each pixel in the second reference image.

Step S670: and replacing the corresponding pixels in the second reference image with the final transformation result until all the pixels in the second reference image are replaced, so as to obtain a third reference image of the single pixel channel.

Step S680: performing histogram equalization on the third reference image according to a preset transformation relationship to realize gray enhancement on the third reference image and obtain a fourth reference image; wherein, all pixels in the fourth reference image accord with the preset gray value range.

Step S690: and determining a preset conversion coefficient as an index of each pixel point in the fourth reference image, and carrying out index conversion on all pixels in the fourth reference image according to the index to obtain an image processing result.

It should be noted that, steps S610 to S690 correspond to the steps and embodiments shown in fig. 3, and for the specific implementation of steps S610 to S690, please refer to the steps and embodiments shown in fig. 3, and the description thereof is omitted here.

Therefore, by implementing the processing method for the pixels in the image shown in fig. 6, the processing result suitable for content identification can be output through processing the target image, so that automatic identification of the content with the specific color in the image can be conveniently realized, and the extraction efficiency of the content with the specific color in the image can be further improved. In addition, the required image processing result can be determined through specific pixel replacement of the image, nonlinear transformation processing, gray enhancement processing and exponential transformation processing of the pixel value of the image, and the identification precision can be improved for the content identification of the specific color of the image processing result, so that the extraction precision of the content of the specific color can be improved.

Further, in this example embodiment, there is further provided a processing apparatus for a pixel in an image, referring to fig. 7, the processing apparatus 700 for a pixel in an image may include:

a pixel selection unit 701, configured to determine a plurality of target pixels in a preset pixel value range in a target image;

the average filtering unit 702 is configured to perform average filtering processing on the target image to obtain a first reference image;

a pixel replacement unit 703, configured to replace each target pixel in the target image with a pixel in the first reference image, where the position of each target pixel is consistent with that of each target pixel, so as to obtain a second reference image;

and a pixel processing unit 704, configured to sequentially perform a pixel value nonlinear transformation process, a gray enhancement process, and an exponential transformation process on the second reference image, so as to obtain an image processing result.

It can be seen that, by implementing the processing device for the pixels in the image shown in fig. 7, the processing result suitable for content identification can be output through the processing of the target image, so that automatic identification of the content with the specific color in the image is facilitated, and the extraction efficiency of the content with the specific color in the image can be improved. In addition, the required image processing result can be determined through specific pixel replacement of the image, nonlinear transformation processing, gray enhancement processing and exponential transformation processing of the pixel value of the image, and the identification precision can be improved for the content identification of the specific color of the image processing result, so that the extraction precision of the content of the specific color can be improved.

In an exemplary embodiment of the present disclosure, the pixel processing unit 704 sequentially performs a pixel value nonlinear transformation process, a gray enhancement process, and an exponential transformation process on the second reference image, to obtain an image processing result, including:

In an exemplary embodiment of the present disclosure, the pixel processing unit 704 performs a nonlinear transformation process on pixel values of all pixels in the second reference image according to a preset reduction rule, to obtain a third reference image of a single pixel channel, including:

In an exemplary embodiment of the present disclosure, the pixel processing unit 704 performs gray enhancement processing on all pixels in the third reference image according to a preset transformation relationship to obtain a fourth reference image, including:

In an exemplary embodiment of the present disclosure, the pixel processing unit 704 performs pixel differentiation processing on all pixels in the fourth reference image according to a preset transform coefficient to obtain an image processing result, including:

In an exemplary embodiment of the present disclosure, the pixel replacement unit 703 replaces each target pixel in the target image with a pixel in the first reference image that coincides with each target pixel position, resulting in a second reference image, including:

In an exemplary embodiment of the present disclosure, the preset pixel value range includes a red channel value range, a green channel value range, and a blue channel value range, and the pixel selection unit 701 determines a plurality of target pixels in the preset pixel value range in the target image, including:

It should be noted that although in the above detailed description several modules or units of a device for action execution are mentioned, such a division is not mandatory. Indeed, the features and functionality of two or more modules or units described above may be embodied in one module or unit in accordance with embodiments of the present disclosure. Conversely, the features and functions of one module or unit described above may be further divided into a plurality of modules or units to be embodied.

Since each functional module of the processing apparatus for pixels in an image according to the exemplary embodiment of the present disclosure corresponds to a step of the foregoing exemplary embodiment of the processing method for pixels in an image, for details not disclosed in the embodiment of the apparatus of the present disclosure, please refer to the foregoing embodiment of the processing method for pixels in an image according to the present disclosure.

Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any adaptations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

It is to be understood that the present disclosure is not limited to the precise arrangements and instrumentalities shown in the drawings, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A method for processing pixels in an image, comprising:

replacing each target pixel in the target image with a pixel with the same position as each target pixel in the first reference image to obtain a second reference image;

sequentially performing pixel value nonlinear transformation processing, gray enhancement processing and exponential transformation processing on the second reference image to obtain an image processing result;

each target pixel in the target image is replaced by a pixel with the same position as each target pixel in the first reference image, so as to obtain a second reference image, which comprises the following steps:

determining a plurality of reference pixels in the same position as the plurality of target pixels from the first reference image; wherein, the plurality of reference pixels and the plurality of target pixels are in one-to-one correspondence;

And replacing the plurality of target pixels in the target image with a plurality of reference pixels based on the one-to-one correspondence, so as to obtain the second reference image.

2. The method according to claim 1, wherein sequentially performing a pixel value nonlinear conversion process, a gray scale enhancement process, and an exponential conversion process on the second reference image to obtain an image processing result, comprises:

performing nonlinear transformation processing on pixel values of all pixels in the second reference image according to a preset reduction rule to obtain a third reference image of a single pixel channel;

and carrying out pixel differentiation processing on all pixels in the fourth reference image according to a preset transformation coefficient to obtain the image processing result.

3. The method of claim 2, wherein performing a nonlinear transformation of pixel values on all pixels in the second reference image according to a preset reduction rule to obtain a third reference image of a single pixel channel, comprises:

and replacing the corresponding pixels in the second reference image with the final transformation result until all the pixels in the second reference image are replaced, so as to obtain a third reference image of a single pixel channel.

4. The method according to claim 2, wherein performing gray enhancement processing on all pixels in the third reference image according to a preset transformation relationship to obtain a fourth reference image comprises:

performing histogram equalization on the third reference image according to the preset transformation relation to realize gray enhancement on the third reference image and obtain the fourth reference image; wherein, all pixels in the fourth reference image conform to a preset gray value range.

5. The method according to claim 2, wherein performing pixel differentiation processing on all pixels in the fourth reference image according to a preset transform coefficient to obtain an image processing result includes:

determining the preset transformation coefficient as an index of each pixel point in the fourth reference image;

And performing index transformation on all pixels in the fourth reference image according to the index to obtain the image processing result.

6. The method of claim 1, wherein the predetermined pixel value range includes a red channel value range, a green channel value range, and a blue channel value range, and determining a plurality of target pixels in the predetermined pixel value range in the target image includes:

7. A processing apparatus for pixels in an image, comprising:

a pixel replacing unit, configured to replace each target pixel in the target image with a pixel in the first reference image, where the pixel is consistent with the position of each target pixel, to obtain a second reference image;

The pixel processing unit is used for sequentially carrying out pixel value nonlinear transformation processing, gray enhancement processing and exponential transformation processing on the second reference image to obtain an image processing result;

the pixel replacing unit replaces each target pixel in the target image with a pixel with the same position as each target pixel in the first reference image to obtain a second reference image, and the pixel replacing unit comprises:

8. A computer-readable medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements a processing method for pixels in an image as claimed in any one of claims 1 to 6.

9. An electronic device, comprising:

one or more processors;

storage means for storing one or more programs which when executed by the one or more processors cause the one or more processors to implement the method of processing pixels in an image as claimed in any one of claims 1 to 6.