CN112488311A

CN112488311A - Image processing method, device, medium and electronic equipment

Info

Publication number: CN112488311A
Application number: CN202011376860.7A
Authority: CN
Inventors: 高文杰; 王银瑞
Original assignee: Taikang Health Industry Investment Holdings Co ltd; Taikang Insurance Group Co Ltd
Current assignee: Taikang Health Industry Investment Holdings Co ltd; Taikang Insurance Group Co Ltd
Priority date: 2020-11-30
Filing date: 2020-11-30
Publication date: 2021-03-12

Abstract

The embodiment of the invention provides a method, a device, a medium and electronic equipment for processing an image, and relates to the technical field of computers, wherein the processing method comprises the following steps: acquiring a first data image obtained by shooting scene data; processing the pixels of the first data image to obtain image pixel values; obtaining a trained sensor model, wherein the form of the trained sensor model is a continuous function; and obtaining an optimized second material image according to the sensor model and the image pixel value. According to the technical scheme of the embodiment of the invention, the image identification efficiency can be improved by optimizing the image for image identification.

Description

Image processing method, device, medium and electronic equipment

Technical Field

The invention relates to the technical field of computer software, in particular to an image processing method and device, a computer readable storage medium and electronic equipment.

Background

At present, when a photo is identified, an equipment camera is used for taking a photo or an existing photo is directly selected from an album, a front-end technology developer transmits the photo to a rear-end technician in a certain mode, then the rear end identifies and processes the photo, and a processing result is returned to the front end for displaying and processing, but the process may have the condition that the photo cannot be identified or the identification is wrong, so that the correct result can be obtained only by taking and uploading for multiple times.

As shown in fig. 1, after the image is collected and uploaded in the image collection process, the intelligent recognition program recognizes the collected image. Here, the acquired image may be an image 1, an image 2, an image 3, an image 4, or the like. In the image recognition process, the situations of low image recognition rate, no image recognition or image recognition error often occur. At this time, the image needs to be collected again and uploaded, and finally a qualified image is collected, so that the image is successfully identified by the intelligent identification program.

The success rate and the efficiency of image recognition are reduced through the processes of image acquisition for many times and intelligent recognition, and how to improve the success rate and the efficiency of image recognition is a technical problem which needs to be solved urgently at present.

It is to be noted that the information disclosed in the above background section is only for enhancement of understanding of the background of the present invention and therefore may include information that does not constitute prior art known to a person of ordinary skill in the art.

Disclosure of Invention

The embodiment of the invention aims to provide an image processing method, an image processing device, a computer readable storage medium and electronic equipment, so that the success rate and efficiency of image recognition are improved at least to a certain extent.

Additional features and advantages of the invention will be set forth in the detailed description which follows, or may be learned by practice of the invention.

According to a first aspect of the embodiments of the present invention, there is provided a processing method of an image, the processing method including: acquiring a first data image obtained by shooting scene data; processing pixels of the first data image to obtain image pixel values, wherein the image pixel values comprise color values of different colors; obtaining a trained sensor model, wherein the form of the trained sensor model is a continuous function, and the sensor model determines an output result according to a set threshold, the color values of different colors and weights corresponding to the color values; obtaining an optimized second material image according to the sensor model and the image pixel value, wherein the second material image comprises at least one of a processed underwriting material image, a claim settlement material image and a telemedicine material image; and carrying out image recognition on the second data image to obtain scene data.

In some embodiments, the sensor model is

output is an output result, j is 3, x is a color value of the different color, w is a weight corresponding to x, and threshold is a threshold.

In some embodiments, before the obtaining the trained sensor model, the processing method further comprises: prior to said obtaining the trained perceptron model according to the sensation, the processing method further comprises: performing model training of the sensor model by a trial-and-error method to obtain a first weight and a first threshold value which satisfy a first formula:

where σ is the output result, j is 3, w is the weight, and t is-threshold.

In some embodiments, said deriving an optimized second profile image from said sensor model and said image pixel values comprises: substituting the first weight and a first threshold value into the sensor model to obtain a first sensor formula; and substituting the image pixel value into the first sensor formula to obtain the image pixel value of the second data image.

In some embodiments, prior to said obtaining the trained perceptron model, the processing method further comprises: performing model training of the sensor model by a trial-and-error method to obtain a second weight and a second threshold which satisfy a second formula: σ (z) ═ 1/(1+ e ^ (-z)), where σ (z) is the output result, z ═ wx + t, x is the color value of the different color, w is the weight for x, t ═ threshold, which is the threshold.

In some embodiments, said deriving an optimized second profile image from said sensor model and said image pixel values comprises: substituting the second weight and a second threshold value into the sensor model to obtain a second sensor formula; and substituting the image pixel value into the second sensor formula to obtain the image pixel value of the second data image.

In some embodiments, the scene material includes insurance scene material and/or medical scene material, and before the acquiring the first material image obtained by shooting the scene material, the processing method further includes: and shooting the physical examination data or the result display part of the physical examination equipment on site to obtain the first data image, wherein the first data image comprises at least one of an underwriting data image, a claim settlement data image and a remote medical data image.

According to a second aspect of the embodiments of the present invention, there is provided a processing apparatus of an image, the processing apparatus including: the image acquisition unit is used for acquiring a first data image obtained by shooting scene data; the pixel processing unit is used for processing the pixels of the first data image to obtain image pixel values, and the image pixel values comprise color values of different colors; the model acquisition unit is used for acquiring a trained sensor model, the form of the trained sensor model is a continuous function, and the sensor model determines an output result according to a set threshold, the color values of different colors and corresponding weights of the color values; the optimization unit is used for obtaining an optimized second material image according to the sensor model and the image pixel value, wherein the second material image comprises at least one of a processed underwriting material image, a claim settlement material image and a remote medical material image; and the identification unit is used for carrying out image identification on the second data image to obtain scene data.

In some embodiments, the processing apparatus further includes a training unit configured to perform model training of the sensor model by trial and error, resulting in a first weight and a first threshold that satisfy a first formula:

where σ is the output result, j is 3, w is the weight, and t is-threshold.

In some embodiments, the optimization unit is further configured to: substituting the first weight and a first threshold value into the sensor model to obtain a first sensor formula; and substituting the image pixel value into the first sensor formula to obtain the image pixel value of the second data image.

In some embodiments, the training unit is further configured to: performing model training of the sensor model by a trial-and-error method to obtain a second weight and a second threshold which satisfy a second formula: σ (z) ═ 1/(1+ e ^ (-z)), where σ (z) is the output result, z ═ wx + t, x is the color value of the different color, w is the weight for x, t ═ threshold, which is the threshold.

In some embodiments, the optimization unit is further configured to: substituting the second weight and a second threshold value into the sensor model to obtain a second sensor formula; and substituting the image pixel value into the second sensor formula to obtain the image pixel value of the second data image.

According to a third aspect of embodiments of the present invention, there is provided a computer-readable medium, on which a computer program is stored, which when executed by a processor, implements the method of processing an image as described in the first aspect of the embodiments above.

According to a fourth aspect of embodiments of the present invention, there is provided an electronic apparatus, including: 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 carry out a method of processing an image as described in the first aspect of the embodiments above.

The technical scheme provided by the embodiment of the invention has the following beneficial effects:

in the technical scheme provided by some embodiments of the present invention, the collected first material image is subjected to pixel processing to obtain an image pixel value, and a trained sensor model is used to optimize the image pixel value to obtain a second material image, so as to perform intelligent recognition on the second material image, thereby improving the success rate and efficiency of image recognition.

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 invention, as claimed.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention. It is obvious that the drawings in the following description are only some embodiments of the invention, and that for a person skilled in the art, other drawings can be derived from them without inventive effort. In the drawings:

FIG. 1 is a schematic diagram schematically illustrating an image recognition process in the related art;

FIG. 2 schematically shows a flow diagram of a method of processing an image according to an embodiment of the invention;

FIG. 3 schematically shows a schematic diagram of an image recognition process according to an embodiment of the invention;

FIG. 4 schematically shows a schematic diagram of a model training process according to an embodiment of the invention;

FIG. 5 schematically illustrates a graph of σ (z) versus z linearity in accordance with an embodiment of the present invention;

FIG. 6a schematically shows a schematic representation before an image optimization process according to an embodiment of the invention;

FIG. 6b schematically shows the image after optimization according to an embodiment of the invention;

fig. 7 schematically shows a block diagram of an apparatus for processing an image according to an embodiment of the present invention;

FIG. 8 schematically illustrates a block diagram of a computer system suitable for use with an electronic device that implements an embodiment of the invention.

Detailed Description

Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different 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 example embodiments to those skilled in the art.

Furthermore, 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 provide a thorough understanding of embodiments of the invention. One skilled in the relevant art will recognize, however, that the invention may be practiced without one or more of the specific details, or with other methods, components, devices, steps, and so forth. In other instances, well-known methods, devices, implementations or operations have not been shown or described in detail to avoid obscuring aspects of the invention.

The block diagrams shown in the figures are functional entities only and do not necessarily correspond to physically separate entities. I.e. these functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor means and/or microcontroller means.

The flow charts shown in the drawings are merely illustrative and do not necessarily include all of the contents and operations/steps, nor do they necessarily have to be performed in the order described. For example, some operations/steps may be decomposed, and some operations/steps may be combined or partially combined, so that the actual execution sequence may be changed according to the actual situation.

In the related art, the acquired image often needs to be successfully identified by an intelligent identification program through a plurality of identification processes.

In order to solve the above problem, embodiments of the present invention provide an image processing method to perform optimization processing on an image, so that the image is easily recognized by an intelligent recognition program, and the success rate and efficiency of image recognition are improved.

Fig. 2 schematically illustrates a method of processing an image according to an exemplary embodiment of the present disclosure. The method provided by the embodiment of the present disclosure can be executed by any electronic device with computer processing capability, such as a terminal device and/or a server. Referring to fig. 2, the image processing method may include the steps of:

step S202, a first data image obtained by shooting scene data is obtained.

Step S204 is to process the pixels of the first data image to obtain image pixel values, where the image pixel values include color values of different colors.

Step S206, obtaining a trained sensor model, wherein the form of the trained sensor model is a continuous function, and the sensor model determines an output result according to a set threshold, color values of different colors and weights corresponding to the color values. In particular, the perceptron model may be

output is the output result, j is 3, x is the color value of different colors, w is the weight corresponding to x, and threshold is the threshold.

Step S208, obtaining an optimized second material image according to the sensor model and the image pixel value, wherein the second material image comprises at least one of a processed underwriting material image, a processed claim settlement material image and a remote medical material image.

Step S210, image recognition is performed on the second data image to obtain scene data.

In the embodiment of the invention, the second data image which meets the intelligent image identification condition is obtained by extracting the image pixel value of the first data image, training the sensor model and optimizing the image pixel value by using the sensor model, so that the identification success rate and efficiency of the subsequent intelligent image identification process are improved.

As shown in fig. 3, after the image is acquired, the image processing method in the embodiment of the present invention is used to perform optimization processing in step S301, and then the intelligent recognition program is used to perform recognition, which shows that the success rate of image recognition is greatly improved compared with fig. 1.

The scene data includes insurance scene data and/or medical scene data, and before step S202, the physical examination data or the result display part of the physical examination equipment needs to be photographed on site to obtain a first data image. Wherein, the first data image comprises at least one of an underwriting data image, a claims data image and a telemedicine data image.

For example, when a customer goes through a business, information of a customer health report needs to be entered into a computer. The information of the physical examination report is manually input by workers and is tedious, and at present, a high-speed camera is generally used for photographing paper physical examination data and directly uploading pictures or synthesizing PDF (Portable document Format) for uploading so as to obtain the information of the physical examination report.

In addition, the physical examination equipment such as electronic blood pressure meters can be used for carrying out on-site physical examination on the client, and the result display part of the physical examination equipment is photographed and uploaded.

According to the scheme of the embodiment of the invention, the picture is subjected to pixel processing after the picture is taken or selected, so that the success rate of picture information identification can be improved, and the business procedures can be completed quickly.

Specifically, in step S204, after completion of photographing or selection of an album, reprocessing of the image is performed using JavaScript. Specifically, the color class and color information of the pixels of the first material image may be obtained, and the image pixel values may be obtained based on the color class and the color information.

First, it is established that an image class is required to store image data. This image class supports the most basic image operations including, but not limited to: and newly building an image, and setting and taking out pixel points.

In addition, a color class needs to be established for performing basic color operations:

then, synthesizing the above function processing to obtain the image pixel value:

before step S206, the sensor model needs to be trained, and a sensor model with a linear formula is obtained.

In the sensor model, the image factors r, g, b are written as vectors < x1, x2, x3>, abbreviated as x, and the weights w1, w2, w3 are also written as vectors < w1, w2, w3>, abbreviated as w, defining the operation w · x ═ Σ wx, i.e. the point operation of w and x is equal to the sum of the products of the factors and the weights. T is defined to be equal to a negative set threshold, i.e. t ═ threshold. The output of the sensor is determined by the sensor model:

the most difficult part is the process of determining the weights w and the threshold t.

The embodiment of the invention determines the weight and the threshold value by adopting a trial and error method. All other parameters are unchanged, small variations in w and t, denoted Δ w and Δ t, respectively, and then observe what the output changes.

This process is repeated until the set of w and t corresponding to the most accurate outputs is obtained as our target value, as shown in fig. 4. This process is the training process of the perceptron model.

In order to ensure the correctness of the training, the "output" must be modified to a continuity function, so that firstly, the calculation result wx + t of the perceptron is denoted as z, i.e. z ═ wx + t.

And recording the output result of the sensor model as sigma (z), and determining a continuous function according to the relation between the output result sigma (z) of the sensor model and the sensor calculation result z. The relationship between the output result σ (z) of the sensor model and the sensor calculation result z can be expressed by the following second formula.

σ (z) ═ 1/(1+ e ^ (-z)), where z ═ wx + t, where w is the weight, t is the threshold, and x is the color value of the different color.

And carrying out model training on the sensor model by a trial and error method to obtain a second weight and a second threshold value which meet a second formula.

After the second weight and the second threshold are obtained, substituting the second weight and the second threshold into the sensor model to obtain a second sensor formula; and substituting the image pixel value into a second sensor formula to obtain the image pixel value of the second data image.

If z tends towards positive infinity z → + ∞ (indicating a strong perceptron match), then σ (z) → 1; if z tends to minus infinity z → - ∞ (indicating a strong perceptron mismatch), then σ (z) → 0. That is, as long as σ (z) is used as an output result, the output becomes a continuity function. The graph shown in fig. 5 shows the case where the sensors are strongly matched.

By performing model training of the sensor model through a trial-and-error method, a first weight and a first threshold value which satisfy the following first formula can be obtained:

wherein, w_jIs the weight, t is the threshold.

Where Δ σ is Δ output,

is that

output。

I.e. between Δ σ and Δ w and Δ t, is a linear relationship and the rate of change is the partial derivative. Thus, the values of w and t can be accurately calculated. Shown in table 1 is a table of test data and accuracy.

Table 1 test data and accuracy table

	1	2	3	4
					w1	0.299	0.147	0.615	0.857
w2	0.587	0.289	0.515	0.621
					w3	0.114	0.436	0.100	0.110
Rate of accuracy	0.92	0.93	0.86	0.95

The technical scheme of the embodiment of the invention has the advantages that when a user takes a picture or uploads a picture through an album, the picture is processed by the trained model of the technical scheme of the invention and then uploaded to the server, so that the user can accurately return the desired information, the user experience is good, and the pressure of the server is reduced.

After the first weight and the first threshold are obtained, substituting the first weight and the first threshold into a sensor model to obtain a first sensor formula; and substituting the image pixel value into the first sensor formula to obtain the image pixel value of the second data image.

Fig. 6a and 6b are compared before and after processing details of the optimization processing performed on the first data image according to the embodiment of the present invention.

In step S208, after the optimized second material image is obtained according to the sensor model and the image pixel value, the second material image may be subjected to image recognition to obtain scene material data. Here, the method of image recognition may be OCR recognition, and is not limited thereto.

According to the image processing method provided by the embodiment of the invention, the collected first data image is subjected to pixel processing to obtain the image pixel value, the trained sensor model is used for optimizing the image pixel value to obtain the second data image, and the second data image is subjected to intelligent identification, so that the success rate and the efficiency of image identification can be improved.

Embodiments of the apparatus of the present invention are described below, which can be used to perform the above-mentioned image processing method of the present invention. As shown in fig. 7, an image processing apparatus 700 according to an embodiment of the present invention includes:

an image acquiring unit 702 is configured to acquire a first material image obtained by shooting scene material.

The pixel processing unit 704 is configured to process pixels of the first data image to obtain image pixel values, where the image pixel values include color values of different colors.

A model obtaining unit 706, configured to obtain a trained sensor model, where the form of the trained sensor model is a continuous function, where the sensor model determines an output result according to a set threshold, color values of different colors, and weights corresponding to the color values, and specifically, the sensor model may be a sensor model

The optimizing unit 708 is configured to obtain an optimized second material image according to the sensor model and the image pixel value, where the second material image includes at least one of a processed underwriting material image, a claim settlement material image, and a telemedicine material image.

The recognizing unit 710 is configured to perform image recognition on the second data image to obtain scene data.

The processing device may further include a training unit configured to perform model training of the sensor model by a trial-and-error method, and obtain a first weight and a first threshold that satisfy the following first formula:

where σ is the output result, j is 3, w is the weight, and t is-threshold.

The optimization unit may be further configured to: substituting the first weight and the first threshold value into a sensor model to obtain a first sensor formula; and substituting the image pixel value into the first sensor formula to obtain the image pixel value of the second data image.

The training unit may further be adapted to: model training of the sensor model is carried out through a trial-and-error method, and a second weight and a second threshold which meet a second formula as follows are obtained: σ (z) ═ 1/(1+ e ^ (-z)), where σ (z) is the output result, z ═ wx + t, x is the color value of different colors, w is the weight corresponding to x, t ═ threshold, threshold is the threshold.

The optimization unit may be further configured to: substituting the second weight and the second threshold value into the sensor model to obtain a second sensor formula; and substituting the image pixel value into a second sensor formula to obtain the image pixel value of the second data image.

For details which are not disclosed in the embodiments of the apparatus of the present invention, reference is made to the embodiments of the method of processing an image described above for details which are not disclosed in the embodiments of the apparatus of the present invention, since the respective functional modules of the apparatus of processing an image of the present invention correspond to the steps of the exemplary embodiment of the method of processing an image described above.

According to the image processing device provided by the embodiment of the invention, the collected first data image is subjected to pixel processing to obtain the image pixel value, the trained sensor model is used for optimizing the image pixel value to obtain the second data image, so that the second data image is intelligently identified, and the success rate and efficiency of image identification can be improved.

Referring now to FIG. 8, shown is a block diagram of a computer system 800 suitable for use in implementing an electronic device of an embodiment of the present invention. The computer system 800 of the electronic device shown in fig. 8 is only an example, and should not bring any limitation to the function and the scope of use of the embodiments of the present invention.

As shown in fig. 8, the computer system 800 includes a Central Processing Unit (CPU)801 that can perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM)802 or a program loaded from a storage section 808 into a Random Access Memory (RAM) 803. In the RAM 803, various programs and data necessary for system operation are also stored. The CPU 801, ROM 802, and RAM 803 are connected to each other via a bus 804. An input/output (I/O) interface 808 is also connected to bus 804.

The following components are connected to the I/O interface 805: an input portion 806 including a keyboard, a mouse, and the like; an output section 807 including a signal such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage portion 808 including a hard disk and the like; and a communication section 809 including a network interface card such as a LAN card, a modem, or the like. The communication section 809 performs communication processing via a network such as the internet. A drive 810 is also connected to the I/O interface 805 as necessary. A removable medium 811 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 810 as necessary, so that a computer program read out therefrom is mounted on the storage section 808 as necessary.

In particular, according to an embodiment of the present invention, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the invention 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 illustrated in the flow chart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication section 809 and/or installed from the removable medium 811. The computer program executes the above-described functions defined in the system of the present application when executed by the Central Processing Unit (CPU) 801.

It should be noted that the computer readable medium shown in the present invention can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination 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 present invention, 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 invention, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. 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 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 invention. 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 described in the embodiments of the present invention may be implemented by software, or may be implemented by hardware, and the described units may also be disposed in a processor. Wherein the names of the elements do not in some way constitute a limitation on the elements themselves.

As another aspect, the present application also provides a computer-readable medium, which may be contained in the electronic device described in the above embodiments; or may exist separately without being assembled into the electronic device. The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to implement the image processing method as described in the above embodiments.

For example, the electronic device may implement the various steps as shown in fig. 2.

It should be noted that although in the above detailed description several modules or units of the 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, according to embodiments of the invention. Conversely, the features and functions of one module or unit described above may be further divided into embodiments by a plurality of modules or units.

Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solution according to the embodiment of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the embodiment of the present invention.

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

It will be understood that the invention is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the invention is limited only by the appended claims.

Claims

1. A method for processing an image, the method comprising:

acquiring a first data image obtained by shooting scene data;

processing pixels of the first data image to obtain image pixel values, wherein the image pixel values comprise color values of different colors;

obtaining a trained sensor model, wherein the form of the trained sensor model is a continuous function, and the sensor model determines an output result according to a set threshold, the color values of different colors and weights corresponding to the color values;

obtaining an optimized second material image according to the sensor model and the image pixel value, wherein the second material image comprises at least one of a processed underwriting material image, a claim settlement material image and a telemedicine material image;

and carrying out image recognition on the second data image to obtain scene data.

2. The processing method according to claim 1, wherein the sensor model is

3. The process of claim 1, wherein prior to said obtaining the trained perceptron model, the process further comprises: performing model training of the sensor model by a trial-and-error method to obtain a first weight and a first threshold value which satisfy a first formula:

where σ is the output result, j is 3, w is the weight, t is-threshold, and threshold is the threshold.

4. The processing method of claim 3, wherein said deriving an optimized second profile image from said sensor model and said image pixel values comprises:

substituting the first weight and a first threshold value into the sensor model to obtain a first sensor formula;

and substituting the image pixel value into the first sensor formula to obtain the image pixel value of the second data image.

5. The process of claim 1, wherein prior to said obtaining the trained perceptron model, the process further comprises: performing model training of the sensor model by a trial-and-error method to obtain a second weight and a second threshold which satisfy a second formula:

σ (z) is 1/(1+ e ^ (-z)), where σ (z) is the output result, z is wx + t, x is the color value of the different color, w is the weight for x, and t is threshold.

6. The processing method of claim 5, wherein said deriving an optimized second profile image from said sensor model and said image pixel values comprises:

substituting the second weight and a second threshold value into the sensor model to obtain a second sensor formula;

and substituting the image pixel value into the second sensor formula to obtain the image pixel value of the second data image.

7. The processing method according to claim 1, wherein the scene material includes insurance scene material and/or medical scene material, and before the acquiring the first material image obtained by shooting the scene material, the processing method further includes:

shooting the physical examination data or the result display part of the physical examination equipment on site to obtain the first data image;

the first data image comprises at least one of an underwriting data image, a claim settlement data image and a telemedicine data image.

8. An apparatus for processing an image, the apparatus comprising:

the image acquisition unit is used for acquiring a first data image obtained by shooting scene data;

the pixel processing unit is used for processing the pixels of the first data image to obtain image pixel values, and the image pixel values comprise color values of different colors;

the model acquisition unit is used for acquiring a trained sensor model, the form of the trained sensor model is a continuous function, and the sensor model determines an output result according to a set threshold, the color values of different colors and corresponding weights of the color values;

the optimization unit is used for obtaining an optimized second material image according to the sensor model and the image pixel value, wherein the second material image comprises at least one of a processed underwriting material image, a claim settlement material image and a remote medical material image;

and the identification unit is used for carrying out image identification on the second data image to obtain scene data.

9. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out a method of processing an image according to any one of claims 1 to 7.

10. 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 carry out a method of processing an image according to any one of claims 1 to 7.