KR101981039B1

KR101981039B1 - Method and apparatus for image processing using histogram

Info

Publication number: KR101981039B1
Application number: KR1020140169466A
Authority: KR
Inventors: 김지호; 차준호; 정재호; 정직한
Original assignee: 한화정밀기계 주식회사
Priority date: 2014-12-01
Filing date: 2014-12-01
Publication date: 2019-08-28
Also published as: KR20160065474A

Abstract

An image processing method according to an embodiment of the present invention may include generating a histogram using pixels included in an image, extracting candidate pixels corresponding to brightness of a detection target to be detected from the image in the histogram; Calculating a dispersion degree indicating a dispersion degree of the candidate pixel using the coordinates in the image with respect to the candidate pixel, identifying a target pixel among the candidate pixels using the dispersion degree, and included in the image The method may include performing an equalization operation on pixels except for the preservation pixel among pixels.

Description

Image processing method using histogram and its apparatus {Method and apparatus for image processing using histogram}

The present invention relates to an image processing method and an apparatus thereof. More specifically, the present invention relates to a method and apparatus for processing an image using a histogram to effectively identify a detection target in a field such as machine vision or video surveillance.

Image equalization is one of the techniques generally used for image enhancement. The sharpness of an image may be improved by redistributing the brightness of the image using a histogram.

However, the conventional smoothing operation does not distinguish between the foreground and the background included in the image, and redistributes the brightness of the entire image, thereby changing the information on the detection target included in the image.

Therefore, when the detection operation is performed from the image on which the smoothing operation is performed, there is a problem in that the detection performance is degraded because information on the detection target included in the image is lost.

Korean Unexamined Patent No. 2009-0017871

The technical problem to be solved by the present invention is a method for performing an equalization operation only on the remaining image except for the detection target such as a defect of a test object, a person or a vehicle included in the image, and an apparatus for performing the same. To provide.

Another technical problem to be solved by the present invention is to provide a method and apparatus for performing the sharpness (Sharpness) for a detection target, such as a defect of a test object, a person or a vehicle included in the image. .

The technical problems of the present invention are not limited to the above-mentioned technical problems, and other technical problems not mentioned will be clearly understood by those skilled in the art from the following description.

According to an aspect of the present invention, there is provided a method of generating an histogram using pixels included in an image, and a candidate corresponding to a brightness of a detection target to be detected from the image in the histogram. Extracting a pixel, calculating a dispersion degree indicating a dispersion degree of the candidate pixel using the coordinates in the image of the candidate pixel, and identifying a preservation pixel among the candidate pixels using the dispersion degree And performing an equalization operation on pixels other than the preservation pixel among pixels included in the image.

In example embodiments, the histogram may include coordinates in the image of each pixel included in the image, and calculating the variance may be performed by using the coordinates included in the histogram. Calculating a degree of dispersion.

The calculating of the dispersion degree may include: mapping the candidate pixel to a virtual area corresponding to the size of the detection target by using the coordinates, and based on the number of the mapped candidate pixels. It may include the step of calculating.

In an embodiment, the method may further include calculating a proximity indicating a degree of proximity between the candidate pixels using coordinates in the image of the candidate pixel, and identifying the pixel to be preserved may include: The method may further include identifying a pixel to be preserved among the candidate pixels by using.

The calculating of the proximity may include classifying the candidate pixels into groups of candidate pixels adjacent to each other using the coordinates, and the number of candidate pixels included in each group and the size of the detection target. Comparing and may include calculating the proximity.

An image processing apparatus according to another aspect of the present invention for achieving the technical problem includes a storage device recorded with one or more processors, a memory and a computer program loaded in the memory and executed by the processor, the computer program Is a series of instructions for generating a histogram using pixels included in an image, an instruction for extracting candidate pixels corresponding to brightness of a detection target to be detected from the image in the histogram, and An instruction for calculating a degree of dispersion indicating a degree of dispersion of the candidate pixel using coordinates in the image, an instruction for identifying a pixel to be preserved among the candidate pixels using the degree of dispersion, and a pixel to be preserved among pixels included in the image For pixels except For example, it may include an instruction for performing an equalization operation.

According to the present invention as described above, the smoothing operation is performed only on the remaining images except for the detection target included in the image, thereby maintaining the necessary information and improving the sharpness of the image.

In addition, since the information on the detection target is maintained, the detection target can be detected without omission even if an additional detection or recognition operation is performed after the smoothing operation.

In addition, according to the present invention as described above, by performing a sharpness operation on the detection target included in the image, there is an effect that can improve the visibility of the detection target included in the image.

1 is a flowchart illustrating an image processing method of an image processing apparatus according to an embodiment of the present invention.
2 is a view for explaining a histogram according to an embodiment of the present invention.
3A to 3C are diagrams for describing a proximity of candidate pixels according to an embodiment of the present invention.
4 is a diagram for describing a dispersion degree of a candidate pixel according to an embodiment of the present invention.
5 is a flowchart illustrating an image processing method of an image processing apparatus according to another exemplary embodiment.
6 is a diagram for describing a dispersion degree of candidate pixels according to another embodiment of the present invention.
7 is a block diagram of an image processing apparatus according to an embodiment of the present invention.
8 is a hardware configuration diagram of an image processing apparatus according to an embodiment of the present invention.

Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings. Advantages and features of the present invention, and methods for achieving them will be apparent with reference to the embodiments described below in detail in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but can be implemented in various forms. The embodiments of the present invention make the posting of the present invention complete and the general knowledge in the technical field to which the present invention belongs. It is provided to fully convey the scope of the invention to those skilled in the art, and the present invention is defined only by the scope of the claims. Like reference numerals refer to like elements throughout.

Unless otherwise defined, all terms (including technical and scientific terms) used in the present specification may be used in a sense that can be commonly understood by those skilled in the art. In addition, the terms defined in the commonly used dictionaries are not ideally or excessively interpreted unless they are specifically defined clearly. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. In this specification, the singular also includes the plural unless specifically stated otherwise in the phrase.

First, terms used in the present invention are defined.

Foreground: The main area that contains the detection target in the image. For example, in the field of machine vision, the foreground may be an area including a defective part of the inspection object, and in the field of video remote monitoring, the foreground may be a person or a car appearing in the surveillance area.

Background: An area except for the foreground of an image.

Contiguity: An index indicating the degree of proximity between two or more pixels included in an image.

Variance: An index indicating the degree of dispersion of two or more pixels included in an image.

Distance of the pixel: The number of pixels located between the A pixel and the B pixel included in the image is the distance between the A pixel and the B pixel.

Hereinafter, a method for performing a smoothing operation except for a detection target such as a defect, a person, or a vehicle of an inspection object included in an image will be described with reference to FIGS. 1 to 4.

1 is a flowchart illustrating an image processing method of an image processing apparatus according to an embodiment of the present invention.

Referring to FIG. 1, the image processing apparatus receives an image including a detection target (S110).

In more detail, the image processing apparatus may receive an image transmitted by an external image providing apparatus through a network in step S110 or may receive an image stored in an auxiliary memory device, but is not limited thereto.

In operation S120, the image processing apparatus generates a histogram that expresses the frequency of the pixels according to the brightness of the pixels included in the image received in operation S110.

In particular, the image processing apparatus according to an embodiment of the present invention may generate a histogram including coordinates in the image of each pixel included in the image received through step S110.

The histogram generated through the step S120 and the coordinates of the pixels included in the histogram will be described in more detail with reference to FIG. 2 after explaining FIG. 1.

The image processing apparatus extracts a candidate pixel corresponding to the brightness of the detection target from the histogram generated through step S120 (S130).

More specifically, the image processing apparatus calculates, from the brightness of the detection target in the histogram, a peak point with the highest frequency of pixels among brightnesses within a predetermined range, and has the brightness with the highest frequency of pixels. Extract candidate pixels, including. In this case, the image processing apparatus may extract the candidate pixel including a pixel having a brightness having the highest frequency of pixels and a pixel having a brightness similar to the brightness having the highest frequency of pixels.

In operation S130, the brightness of the detection target may be set by receiving the brightness of the detection target to be identified in the image from the user. In addition, the brightness of the detection target according to another embodiment of the present invention may be set by receiving the color information of the detection target to be identified in the image from the user and calculating the brightness of the detection target based on the received color information. .

The predetermined range is an error range for selecting the most appropriate brightness of the detection target from the brightness of the detection target received from the user.

The candidate pixel is a candidate pixel that can be identified as a pixel constituting the detection target in the image. In other words, the candidate pixels are pixels constituting the foreground in the image composed of the foreground and the background, and step S130 is a step of extracting only the foreground from the image.

The image processing apparatus calculates the proximity and variance of the candidate pixels extracted through the operation S130 using the coordinates of the pixels included in the image included in the histogram (S140).

In more detail, in operation S140, the result of calculating the proximity or the dispersion degree to the candidate pixel of the image processing apparatus may be either high or low.

In operation S140, the method of calculating the proximity and the dispersion degree of the candidate pixel will be described in more detail with reference to FIGS. 3A to 3C and 4 after describing FIG. 1.

The image processing apparatus identifies the preservation pixel among the candidate pixels by using the proximity and the dispersion of the candidate pixels calculated in operation S140 (S150).

In more detail, the image processing apparatus identifies a candidate pixel having a high proximity and a low dispersion among the candidate pixels as the pixel to be preserved.

In operation S150, the preservation pixel is a pixel constituting an object to be detected in the image. In other words, the preservation pixel is a pixel constituting a detection object such as a defect, a person, or a vehicle of the inspection object. In operation S150, the detection object is extracted from the foreground.

The image processing apparatus performs an equalization operation on pixels except for the preservation target pixel identified in step S150 among pixels included in the histogram generated in step S120 (S160).

In more detail, the image processing apparatus performs a smoothing operation of uniformly adjusting the distribution of contrast values for the pixels included in the histogram except for the pixel to be preserved. That is, the image processing apparatus performs smoothing only on the region and the background in which the detection target is excluded in the foreground.

Therefore, the image processing apparatus according to an embodiment of the present invention performs the smoothing operation only on the remaining images except for the detection target such as a defect of a test object, a person, or a vehicle included in the image, thereby maintaining necessary information and simultaneously maintaining the image. The effect can be improved to improve the sharpness of.

The image processing apparatus performs a sharpness operation on the storage target pixel identified in operation S150 (S170).

In more detail, the image processing apparatus performs a sharpness operation of adjusting contrast of pixels with respect to the storage target pixel identified in operation S150 and excluded from the smoothing operation of operation S160. That is, the image processing apparatus performs a sharpness operation on the detection target included in the image.

Therefore, the image processing apparatus according to the exemplary embodiment may improve the visibility of the detection target included in the image by performing a sharpness operation on a detection target such as a defect, a person, or a vehicle included in the image. It can exert an effect.

In operation S180, the image processing apparatus reconstructs an image including the pixel on which the smoothing operation is performed and the pixel to which the sharpening operation is performed, in operation S170.

Hereinafter, the histogram generated through the step S120 and the coordinates of the pixels included in the histogram will be described in detail with reference to FIG. 2.

2 is a view for explaining a histogram according to an embodiment of the present invention.

Referring to FIG. 2, the histogram according to an embodiment of the present invention uses the brightness of the pixel as the X axis and the frequency of the pixel as the Y axis. The histogram has a form of a cumulative bar graph that can express the frequency number of pixels having a specific brightness among the pixels included in the image.

In particular, as shown in FIG. 2, when each pixel included in the image is represented by one block 25 constituting the cumulative bar graph of the histogram, each block 25 in the histogram corresponds to a corresponding pixel. It may include an identifier 27 for identifying the and the x, y coordinates 29 in the image of the pixel.

The image processing apparatus calculates, from the brightness of the detection target in the histogram, the brightness 21 having the highest frequency of pixels among the brightnesses within the predetermined range 23, and the pixel having the brightness 21 having the highest frequency of pixels. Candidate pixels may be extracted including pixels having brightness similar to brightness 21 having the highest frequency of pixels.

Therefore, the image processing apparatus according to an embodiment of the present invention includes the coordinates of the pixels in the histogram so that the image processing apparatus may perform operations required for image processing using only the coordinates of the pixels included in the histogram without referring to the input image. It can exert an effect.

Hereinafter, the method of calculating the proximity and dispersion of the candidate pixel in step S140 will be described in detail with reference to FIGS. 3A to 3C and 4.

3A to 3C are diagrams for describing a proximity of candidate pixels according to an embodiment of the present invention.

Referring to FIG. 3A, each candidate pixel includes an identifier for identifying a pixel and x, y coordinates in an image of the pixel.

In this case, the distance between x0, y0 of C0 candidate pixel and x1, y1 of C1 candidate pixel is 0, x4, y4 of C4 candidate pixel, x5, y5 of C5 candidate pixel, x7, y7 of C7 candidate pixel, and Assume that the distance between x8 and y8 of the C8 candidate pixel is zero.

Referring to FIG. 3B, candidate pixels may be classified into one or more groups composed of candidate pixels having a distance of zero.

Therefore, the image processing apparatus classifies the candidate pixels into groups of candidate pixels adjacent to each other.

That is, the image processing apparatus includes a group 1 (31) consisting of C0 candidate pixels and a C1 candidate pixel, a group 2 (33) consisting of C2 candidate pixels, and a group 3 (35) consisting of C3 candidate pixels. , Group 37 consisting of C4 candidate pixels, C5 candidate pixels, C7 candidate pixels, and C8 candidate pixels, and group 4 39 consisting of C6 candidate pixels.

Referring to FIG. 3C, candidate pixels may be represented by being grouped into group 1 31 to group 4 39 including each candidate pixel.

The image processing apparatus calculates the number of candidate pixels included in the group 1 31 to the group 4 39.

If the number of candidate pixels included in each group is larger than the minimum size of the detection target, the image processing apparatus calculates the proximity of the candidate pixels included in the group as high. If the number of candidate pixels included in each group is smaller than the minimum size of the detection target, the image processing apparatus calculates the proximity of the candidate pixels included in the group as low.

Here, the minimum size of the detection target may be set by receiving a minimum size of the detection target to be identified in the image from the user, but is not limited thereto and may be preset in the image processing apparatus.

4 is a diagram for describing a dispersion degree of a candidate pixel according to an embodiment of the present invention.

Referring to FIG. 4, the image processing apparatus maps candidate pixels 43 and 45 to a two-dimensional kernel having a minimum size 41 of a detection object as a size of one side based on coordinates in an image of the candidate pixel. . Here, the kernel is a kind of virtual domain for the convenience of computation.

When the candidate pixels mapped to the respective kernels satisfy the following Equation 1, the image processing apparatus calculates the dispersion degree of the candidate pixels included in the corresponding kernel as High and does not satisfy the following Equation 1. In this case, the dispersion degree of the candidate pixels included in the kernel is calculated as low.

( N is the minimum size of the detection target, P is the number of candidate pixels mapped to the kernel)

However, when the candidate pixels mapped to one kernel are divided into two groups according to the coordinates in the image, the image processing apparatus calculates the number P of candidate pixels mapped to the corresponding kernel as follows.

For convenience of explanation, two groups mapped to one kernel are referred to as group A 43 and group B 45 respectively.

Candidate pixel A 47 closest to group B 45 among the candidate pixels included in group A 43 and candidate pixel B 49 closest to group A 43 among the candidate pixels included in group B 45. ), When the distance is greater than N , the image processing apparatus calculates P as a larger value between the number of candidate pixels included in group A and the number of candidate pixels included in group B.

In contrast, candidate pixels A 47 closest to the group B 45 among the candidate pixels included in the group A 43 and candidate pixels closest to the group A 43 among the candidate pixels included in the group B 45. If the distance of B 49 is less than or equal to N , the image processing apparatus calculates P as a value obtained by adding up the number of candidate pixels included in group A and the number of candidate pixels included in group B.

Hereinafter, a method for performing a smoothing operation including a detection target such as fog or smoke included in an image will be described with reference to FIGS. 5 and 6.

5 is a flowchart illustrating an image processing method of an image processing apparatus according to another exemplary embodiment.

Referring to FIG. 5, the image processing apparatus receives an image including a detection target in operation S210.

In more detail, the image processing apparatus may receive an image transmitted from an external image providing apparatus through a network in step S210 or may receive an image stored in the auxiliary storage device, but is not limited thereto.

The image processing apparatus generates a histogram representing the frequency number of pixels according to the intensity of the pixels included in the image received in operation S210 (S220).

In particular, the image processing apparatus according to an embodiment of the present invention may generate the histogram by including the coordinates in the image of each pixel included in the image received through the step S210 in the histogram.

A detailed description of the histogram generated through the step S220 and the coordinates of the pixels included in the histogram is as described above with reference to FIG. 2.

The image processing apparatus extracts a candidate pixel corresponding to the brightness of the detection target from the histogram generated through operation S220 (S230).

In operation S230, the candidate pixel is a pixel that becomes a candidate that may be identified as a pixel constituting a detection target in the image. In other words, the candidate pixels are pixels constituting the foreground in the image composed of the foreground and the background, and step S130 is a step of extracting only the foreground from the image.

The image processing apparatus calculates the dispersion of the candidate pixels extracted through the step S230 by using the coordinates of the pixels included in the image included in the histogram (S240).

More specifically, when the detection target included in the image is in the form of fog or smoke, the proximity of the candidate pixels is not calculated separately, but only the dispersion of the candidate pixels is calculated. A method of calculating the dispersion degree of the candidate pixel in operation S240 will be described in more detail with reference to FIG. 6 after describing FIG. 5.

The image processing apparatus identifies the preservation pixel among the candidate pixels by using the dispersion degree of the candidate pixel calculated in operation S240 (S250).

More specifically, the image processing apparatus identifies a high candidate pixel among candidate pixels as a preservation pixel. The image processing apparatus identifies low candidate pixels among the candidate pixels as pixels constituting the detection target.

In operation S250, the pixels constituting the detection target are pixels constituting the target to be detected, such as fog or smoke.

The pixel to be preserved is a pixel other than the pixels constituting the object to be detected from the pixels included in the foreground. In other words, the pixel to be preserved may be a pixel constituting a defect, a person, a car, or the like of the inspection object in which fog or smoke is excluded from the foreground.

The image processing apparatus performs a smoothing operation on pixels except for the preservation target pixel identified in step S250 among pixels included in the histogram generated in step S220 (S260).

In more detail, the image processing apparatus performs a smoothing operation of uniformly adjusting the distribution of contrast values for the pixels included in the histogram except for the pixel to be preserved. That is, the image processing apparatus smoothes only the detection target and the background such as fog or smoke included in the foreground.

Therefore, the image processing apparatus according to an embodiment of the present invention can improve the sharpness of the image while maintaining necessary information by performing a smoothing operation only on the detection target such as fog or smoke included in the image and the background of the image. It can exert an effect.

In operation S270, the image processing apparatus reconstructs an image including the pixel on which the smoothing operation is performed and the pixel to be preserved on which the smoothing operation is not performed.

Hereinafter, a method of calculating the dispersion degree of candidate pixels in step S240 will be described in detail with reference to FIG. 6.

6 is a diagram for describing a dispersion degree of candidate pixels according to another embodiment of the present invention.

Referring to FIG. 6, the image processing apparatus maps the candidate pixel 63 to a two-dimensional kernel having a minimum size 61 of a detection target as one side based on coordinates in the image of the candidate pixel. Here, the kernel is a kind of virtual domain for the convenience of computation.

When the candidate pixels mapped to the respective kernels satisfy the following Equation 2, the image processing apparatus calculates the dispersion degree of the candidate pixels included in the corresponding kernel as High and does not satisfy the Equation 2 below. In this case, the dispersion degree of the candidate pixels included in the kernel is calculated as low.

Hereinafter, a logical configuration of an image processing apparatus according to an embodiment of the present invention will be described in detail with reference to FIGS. 7 and 8.

7 is a block diagram of an image processing apparatus 300 according to an embodiment of the present invention.

Referring to FIG. 7, the image processing apparatus 300 may include a communication unit 310, an input / output unit 320, a histogram generator 330, a candidate pixel identification unit 340, a proximity calculator 350, and a dispersion calculation. The unit 360 may include a preservation target identification unit 370, an image processing unit 380, and an image reconstruction unit 390.

The communication unit 310 transmits and receives data with an external image providing apparatus through a network, receives an original image for image processing, or transmits an image processed result image.

The input / output unit 320 inputs / outputs data necessary for the image processing apparatus from a user, and receives brightness or color information of a detection target and a minimum size of the detection target.

The histogram generator 330 generates a histogram that expresses the frequency of the pixels according to the brightness of the pixels using the image input through the communication unit 310. In particular, the histogram generator 330 according to an embodiment of the present invention may generate a histogram including coordinates in an image of each pixel included in the image.

The candidate pixel identification unit 340 extracts a candidate pixel corresponding to the brightness of the detection target received through the input / output unit 320 from the histogram generated by the histogram generator 330.

More specifically, the candidate pixel identification unit 340 calculates the brightness having the highest frequency among pixels among brightnesses within a predetermined range from the brightness of the detection target in the histogram, and includes pixels having the brightness with the highest frequency of pixels. Extract candidate pixels. In this case, the candidate pixel identification unit 340 may extract the candidate pixel including the pixel having the brightness having the highest frequency and the pixel having the brightness similar to the brightness having the highest frequency of the pixel.

The proximity calculator 350 calculates a proximity of the candidate pixels extracted through the candidate pixel identifier 340. In more detail, the proximity calculation method for the candidate pixels of the proximity calculator 350 is as described above with reference to FIGS. 3A to 3C.

The dispersion calculator 360 calculates a dispersion of candidate pixels extracted through the candidate pixel identifier 340. More specifically, the dispersion degree calculation method for the candidate pixel of the dispersion calculator 360 is as described above with reference to FIGS. 4 and 6.

The save target identification unit 370 identifies the save target pixel among the candidate pixels. In more detail, when the smoothing operation is to be performed except for the detection target, the preservation object identifying unit 370 stores the candidate pixels having high proximity and low dispersion among the candidate pixels. Identify with.

In contrast, when the smoothing operation is to be performed including the detection target, the storage object identifying unit 370 identifies a high candidate pixel among candidate pixels as the storage target pixel.

The image processor 380 may perform a smoothing operation on the pixels included in the histogram generated by the histogram generator 330 except for the pixels to be stored, which are identified by the target to be identified 370. Also, the image processor 380 may additionally perform a sharpness operation on the pixel to be stored which is identified through the object to be identified 370.

The image reconstructor 390 reconstructs an image including the pixel on which the smoothing operation is performed and the pixel on which the smoothing operation is not performed, through the image processor 380.

Until now, each component of FIG. 7 may refer to software or hardware such as a field-programmable gate array (FPGA) or an application-specific integrated circuit (ASIC). However, the components are not limited to software or hardware, and may be configured to be in an addressable storage medium, or may be configured to execute one or more processors. The functions provided in the above components may be implemented by more detailed components, or may be implemented as one component that performs a specific function by combining a plurality of components.

8 is a hardware configuration diagram of an image processing apparatus 300 according to an embodiment of the present invention.

The image processing apparatus 300 may include a processor 410 for executing a command, a RAM 420, a storage 430 for storing computer program data implementing an image processing method, and a network interface 440 for transmitting and receiving data with an external device. I / O 450 and processor 410, RAM 420, storage 430, network interface 440, and I / O 450 that receive and output data necessary for the operation of the image processing apparatus from the user. ) May include a data BUS 460 connected to the data bus.

The storage 430 may store data such as an execution file and a resource file for executing the computer program. More specifically, the storage 430 includes a series of instructions for generating a histogram using pixels included in an image, and instructions for extracting candidate pixels corresponding to brightness of a detection target to be detected from the image in the histogram. A command for calculating a degree of dispersion indicating a degree of dispersion of the candidate pixel using the coordinates in the image of the candidate pixel, an instruction for identifying a pixel to be preserved among the candidate pixels using the degree of dispersion, and included in the image. A computer program including an instruction for performing an equalization operation on the pixels except for the preservation pixel among the stored pixels may be stored.

Although embodiments of the present invention have been described above with reference to the accompanying drawings, those skilled in the art to which the present invention pertains may implement the present invention in other specific forms without changing the technical spirit or essential features thereof. I can understand that. Therefore, it should be understood that the embodiments described above are exemplary in all respects and not restrictive.

Claims

Generating a histogram using pixels included in the image;
Extracting candidate pixels corresponding to brightness of a detection target to be detected from the image in the histogram;
Calculating a degree of dispersion indicating a degree of dispersion of the candidate pixel using the coordinates in the image of the candidate pixel;
Identifying a pixel to be preserved among the candidate pixels using the dispersion degree; And
Performing an equalization operation on pixels other than the preservation pixel among pixels included in the image,
Calculating a proximity indicating the proximity between the candidate pixels using the coordinates in the image of the candidate pixels;
Identifying the pixel to be preserved,
And identifying the preservation pixel among the candidate pixels by further using the proximity.

delete

According to claim 1,
The step of calculating the proximity,
Classifying the candidate pixels into groups of candidate pixels adjacent to each other by using the coordinates, and calculating the proximity by comparing the number of candidate pixels included in each group and the size of the detection target; Image processing method.

One or more processors;
Memory; And
A storage device loaded with the memory and recorded with a computer program executed by the processor,
The computer program,
A series of instructions for generating a histogram using pixels included in the image;
Instructions for extracting candidate pixels corresponding to brightness of a detection target to be detected from the image in the histogram;
An instruction for calculating a proximity indicating a degree of proximity between the candidate pixels using the coordinates in the image for the candidate pixels;
An instruction for calculating a degree of dispersion indicating a degree of dispersion of the candidate pixel using the coordinates in the image for the candidate pixel;
An instruction for identifying a pixel to be preserved among the candidate pixels using the proximity and the dispersion; And
And an instruction for performing an equalization operation on pixels other than the preservation pixel among pixels included in the image.