CN113052794A - Image definition recognition method based on edge features - Google Patents

Image definition recognition method based on edge features Download PDF

Info

Publication number
CN113052794A
CN113052794A CN202110020428.2A CN202110020428A CN113052794A CN 113052794 A CN113052794 A CN 113052794A CN 202110020428 A CN202110020428 A CN 202110020428A CN 113052794 A CN113052794 A CN 113052794A
Authority
CN
China
Prior art keywords
image
gray
edge
target image
value
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202110020428.2A
Other languages
Chinese (zh)
Inventor
齐凯华
沈鹏
陈江义
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhengzhou University
Original Assignee
Zhengzhou University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Zhengzhou University filed Critical Zhengzhou University
Priority to CN202110020428.2A priority Critical patent/CN113052794A/en
Publication of CN113052794A publication Critical patent/CN113052794A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/70—Denoising; Smoothing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/90—Dynamic range modification of images or parts thereof
    • G06T5/92—Dynamic range modification of images or parts thereof based on global image properties
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/13—Edge detection

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Quality & Reliability (AREA)
  • Image Analysis (AREA)

Abstract

The invention discloses an image definition recognition method based on edge characteristics, which relates to the technical field of image processing and is used for preprocessing a target image, wherein the preprocessing comprises the steps of carrying out gray level transformation and denoising on the target image; acquiring a gray difference value of the processed target image, and determining an edge section of the target image; and summing all the gray scale edge gradient values of the whole image, and averaging the gray scale edge gradient values on the whole image to obtain an image definition identification value. The method has the advantages of unimodal performance, consistency and the like, the definition degree and the evaluation result meet the unbiased condition, the blurred images with different contents can be evaluated, and the visual effect of the image quality is well reflected.

Description

Image definition recognition method based on edge features
Technical Field
The invention relates to the technical field of image processing, in particular to an image definition identification method based on edge features.
Background
Digital image processing is a technology for converting image signals into digital signals and processing the digital signals by using a computer, is widely applied to a plurality of fields such as scientific inspection machines, industrial and agricultural production, aerospace and the like, and becomes an attractive subject with a wide prospect. With the increasing application of image processing, the requirements for image quality are also increasing, but in the process of camera shooting, due to factors such as relative motion between a target object and a camera or surrounding environment, a shot image is blurred, and the degree of blurring of the image has a great influence on subsequent image processing. Therefore, it is necessary to evaluate the degree of sharpness of an image before image processing.
The evaluation of image sharpness is classified into subjective evaluation and objective evaluation. The subjective evaluation is that an evaluator scores the image blur according to an evaluation rule and an evaluation scale, but the image quality is unreliable due to the fact that manual observation is easily affected by personal subjective factors, and long-time observation is easy to cause visual fatigue, so that the subsequent evaluation work is slow in progress and cannot meet the requirement of high-speed development of modern enterprises; the objective evaluation adopts an algorithm to automatically evaluate the image definition, but the calculation complexity is high and the application range is wide at present.
The invention discloses a method and a device for determining picture definition for searching Chinese patent CN111754491A, which are characterized in that an object included in a picture to be determined is detected and identified by using a target detection model to obtain at least one main object, and then images of the main objects, namely main object images, are extracted from the picture to be determined. And carrying out edge detection on each main object image, and calculating the definition of the main object image according to the edge detection image. And finally, obtaining the definition of the whole picture according to the definition of each main object image. According to the scheme, the main object image is identified and extracted from the picture, the definition of the main object image is calculated, and the influence of a fuzzy background or a sharp background contained in the picture on the definition of the whole picture is avoided, so that the accuracy of the picture definition judgment result is improved. But it is computationally expensive and computationally complex.
An effective solution to the problems in the related art has not been proposed yet.
Disclosure of Invention
Aiming at the problems in the related art, the invention provides an image definition identification method based on edge features, so as to overcome the technical problems in the prior related art.
The technical scheme of the invention is realized as follows:
an image definition recognition method based on edge features comprises the following steps:
step S1, preprocessing the target image, wherein the preprocessing comprises gray level conversion and denoising of the target image;
step S2, acquiring the gray level difference of the processed target image and determining the edge section of the target image;
and step S3, summing all the gray scale edge gradient values of the whole image, and averaging the gray scale edge gradient values on the whole image to obtain an image definition identification value.
Further, the step of performing gray scale transformation on the target image is represented as:
gray＝0.299·R+0.587·G+0.114·B。
further, the step of obtaining the gray scale difference of the processed target image includes the following steps:
the gray value of each pixel point is respectively scanned in advance, and the adjacent gray difference is expressed as:
Δgray＝|g(i,j+1)-g(i,j)|,(0≤i≤m,0≤j≤n-1)
wherein g (i, j) represents a gray value at coordinates (x, y);
obtaining the gray difference value delta between two adjacent pointsgrayIn which includesgray≥TgrayIt is denoted as an image edge segment.
Further, the step of summing all the gray scale edge slope values of the whole image includes the following steps:
three points with the gray difference value larger than the gray threshold value are selected in advance;
calculating the slopes of the three straight lines respectively;
the average values of the three lines are obtained and are respectively expressed as:
Figure RE-GDA0003078135170000021
ΔGj+2＝|g(i,j+2)-g(i,j+1)|
ΔGj+1＝|g(i,j+1)-g(i,j)|
where G (i, j) is a gray edge gradient value calculated after the determination of a gray edge.
Summing all gray edge slope values of the whole target image, which is expressed as:
Figure RE-GDA0003078135170000031
further, the method also comprises the following steps:
obtaining sum sun of gray scale edge gradient values in vertical direction of target imageH；
The gray edge slope values are averaged over the entire image, d, as:
Figure RE-GDA0003078135170000032
the invention has the beneficial effects that:
the invention relates to an image definition recognition method based on edge characteristics, which comprises the steps of preprocessing a target image, acquiring a gray level difference value of the processed target image, and determining an edge section of the target image; and summing all the gray scale edge gradient values of the whole image, and averaging the gray scale edge gradient values on the whole image to obtain an image definition identification value. The method has the advantages of unimodal performance, consistency and the like, the definition degree and the evaluation result meet the unbiased condition, the blurred images with different contents can be evaluated, and the visual effect of the image quality is well reflected.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
Fig. 1 is a flowchart illustrating an image sharpness identifying method based on edge features according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments that can be derived by one of ordinary skill in the art from the embodiments given herein are intended to be within the scope of the present invention.
According to the embodiment of the invention, an image definition identification method based on edge features is provided.
As shown in fig. 1, an image sharpness recognition method based on edge features according to an embodiment of the present invention includes the following steps:
step S1, preprocessing the target image, wherein the preprocessing comprises gray level conversion and denoising of the target image;
step S2, acquiring the gray level difference of the processed target image and determining the edge section of the target image;
and step S3, summing all the gray scale edge gradient values of the whole image, and averaging the gray scale edge gradient values on the whole image to obtain an image definition identification value.
Wherein, the step of performing gray scale transformation on the target image is represented as:
gray＝0.299·R+0.587·G+0.114·B。
the data volume of subsequent image processing can be greatly reduced by reducing the RGB three-channel data value of the image into the gray level one channel, and the image is required to be denoised besides the gray level processing of the image, so that the error result obtained due to the interference of noise is avoided.
The step of obtaining the gray scale difference value of the processed target image comprises the following steps:
the gray value of each pixel point is respectively scanned in advance, and the adjacent gray difference is expressed as:
Δgray＝|g(i,j+1)-g(i,j)|,(0≤i≤m,0≤j≤n-1)
wherein g (i, j) represents a gray value at coordinates (x, y);
obtaining the gray difference value delta between two adjacent pointsgrayIn which includesgray≥TgrayIt is denoted as an image edge segment.
Wherein, the step of summing all the gray scale edge gradient values of the whole image comprises the following steps:
three points with the gray difference value larger than the gray threshold value are selected in advance;
calculating the slopes of the three straight lines respectively;
the average values of the three lines are obtained and are respectively expressed as:
Figure RE-GDA0003078135170000041
ΔGj+2＝|g(i,j+2)-g(i,j+1)|
ΔGj+1＝|g(i,j+1)-g(i,j)|
where G (i, j) is a gray edge gradient value calculated after the determination of a gray edge.
Summing all gray edge slope values of the whole target image, which is expressed as:
Figure RE-GDA0003078135170000042
wherein, still include the following step:
obtaining sum sun of gray scale edge gradient values in vertical direction of target imageH；
The gray edge slope values are averaged over the entire image, d, as:
Figure RE-GDA0003078135170000043
by means of the technical scheme, the gray level difference of the processed target image is obtained by preprocessing the target image, and the edge section of the target image is determined; and summing all the gray scale edge gradient values of the whole image, and averaging the gray scale edge gradient values on the whole image to obtain an image definition identification value. The method has the advantages of unimodal performance, consistency and the like, the definition degree and the evaluation result meet the unbiased condition, the blurred images with different contents can be evaluated, and the visual effect of the image quality is well reflected.
In addition, a new gradient calculation method is provided according to the fact that the edge gray value change of a clear image is in a sudden change state, the edge gray value change of a fuzzy image is in a gentle state, the gray value corresponding to each pixel point is regarded as a straight line, whether the measured straight line is flat or not depends on the slope of the straight line, namely three points with gray difference values larger than the slope of the gray threshold value are selected, the slopes of the three straight lines are calculated respectively, and finally, the average value is calculated. Conversely, the smaller the average value of the gradient of the gray scale edge is, the gentler the gray scale change is, and the more blurred the image is.
In summary, according to the above technical solution of the present invention, the target image is preprocessed to obtain the gray scale difference of the processed target image, and determine the edge section of the target image; and summing all the gray scale edge gradient values of the whole image, and averaging the gray scale edge gradient values on the whole image to obtain an image definition identification value. The method has the advantages of unimodal performance, consistency and the like, the definition degree and the evaluation result meet the unbiased condition, the blurred images with different contents can be evaluated, and the visual effect of the image quality is well reflected.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.

Claims (5)

1.一种基于边缘特征的图像清晰度识别方法，其特征在于，包括以下步骤：1. an image sharpness identification method based on edge feature, is characterized in that, comprises the following steps: 对目标图像进行预处理，其中包括对目标图像进行灰度变换和去噪处理；Preprocessing the target image, including grayscale transformation and denoising processing on the target image; 获取处理后目标图像的灰度差值，并确定目标图像的边缘地段；Obtain the grayscale difference value of the processed target image, and determine the edge area of the target image; 对整幅图像所有的灰度边缘坡度值求和，并对灰度边缘坡度值在整幅图像上求平均值作为图像清晰度识别值。All gray-scale edge gradient values of the entire image are summed, and the gray-scale edge gradient values are averaged over the entire image as the image sharpness identification value. 2.根据权利要求1所述的基于边缘特征的图像清晰度识别方法，其特征在于，步骤所述对目标图像进行灰度变换，表示为：2. the image sharpness identification method based on edge feature according to claim 1, is characterized in that, described in step, carries out grayscale transformation to target image, and is expressed as: gray＝0.299·R+0.587·G+0.114·B。gray=0.299·R+0.587·G+0.114·B. 3.根据权利要求1所述的基于边缘特征的图像清晰度识别方法，其特征在于，步骤所述获取处理后目标图像的灰度差值，包括以下步骤：3. The image sharpness identification method based on edge feature according to claim 1, is characterized in that, the grayscale difference value of the target image after the acquisition and processing described in the step comprises the following steps: 预先分别扫描每个像素点的灰度值，相邻的灰度差值，表示为：The gray value of each pixel is scanned separately in advance, and the adjacent gray value difference is expressed as: Δgray＝|g(i,j+1)-g(i,j)|,(0≤i≤m,0≤j≤n-1)Δ gray =|g(i,j+1)-g(i,j)|,(0≤i≤m,0≤j≤n-1) 其中，g(i,j)表示在坐标(x,y)处的灰度值；Among them, g(i,j) represents the gray value at the coordinate (x,y); 获取相邻两点灰度差值Δgray，其中包括Δgray≥Tgray，则表示为图像边缘地段。Obtain the grayscale difference value Δ gray of two adjacent points, including Δ gray ≥T gray , which is represented as an image edge area. 4.根据权利要求1所述的基于边缘特征的图像清晰度识别方法，其特征在于，步骤所述对整幅图像所有的灰度边缘坡度值求和，包括以下步骤：4. The image sharpness identification method based on edge feature according to claim 1, is characterized in that, described in step, sums up all gray-scale edge gradient values of the whole image, comprising the following steps: 预先选取灰度差值大于灰度阈值附近三点；Pre-select three points near the grayscale difference greater than the grayscale threshold; 分别计算三条直线的斜率；Calculate the slopes of the three straight lines respectively; 获取三条直线的平均值，分别表示为：Obtain the average of the three straight lines, which are expressed as:
Figure RE-FDA0003078135160000011
Figure RE-FDA0003078135160000011
 ΔGj+2＝|g(i,j+2)-g(i,j+1)|ΔG j+2 =|g(i,j+2)-g(i,j+1)| ΔGj+1＝|g(i,j+1)-g(i,j)|ΔG j+1 =|g(i,j+1)-g(i,j)| 其中，G(i,j)为判定为灰度边缘后计算出的灰度边缘坡度值。Among them, G(i,j) is the gradient value of the grayscale edge calculated after it is determined to be a grayscale edge. 对整幅目标图像所有的灰度边缘坡度值求和，表示为：The summation of all gray-scale edge slope values of the entire target image is expressed as:
Figure RE-FDA0003078135160000012
Figure RE-FDA0003078135160000012
 5.根据权利要求1所述的基于边缘特征的图像清晰度识别方法，其特征在于，还包括以下步骤：5. the image sharpness identification method based on edge feature according to claim 1, is characterized in that, also comprises the following steps: 获取目标图像垂直方向的灰度边缘坡度值的和sunH；Obtain the sum sun H of the gray-scale edge slope values in the vertical direction of the target image; 对灰度边缘坡度值在整幅图像上求平均值d，表示为：Calculate the average value d of the gray-scale edge slope value over the whole image, which is expressed as:
Figure RE-FDA0003078135160000013
Figure RE-FDA0003078135160000013
CN202110020428.2A 2021-01-07 2021-01-07 Image definition recognition method based on edge features Pending CN113052794A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110020428.2A CN113052794A (en) 2021-01-07 2021-01-07 Image definition recognition method based on edge features

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110020428.2A CN113052794A (en) 2021-01-07 2021-01-07 Image definition recognition method based on edge features

Publications (1)

Publication Number Publication Date
CN113052794A true CN113052794A (en) 2021-06-29

Family

ID=76508303

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110020428.2A Pending CN113052794A (en) 2021-01-07 2021-01-07 Image definition recognition method based on edge features

Country Status (1)

Country Link
CN (1) CN113052794A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115734069A (en) * 2022-11-16 2023-03-03 安徽宝信信息科技有限公司 Automatic tracking and image capturing system
CN116674134A (en) * 2023-08-03 2023-09-01 绵阳华远同创科技有限公司 Automatic casting processing method and system for resin words

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115734069A (en) * 2022-11-16 2023-03-03 安徽宝信信息科技有限公司 Automatic tracking and image capturing system
CN116674134A (en) * 2023-08-03 2023-09-01 绵阳华远同创科技有限公司 Automatic casting processing method and system for resin words
CN116674134B (en) * 2023-08-03 2023-10-20 绵阳华远同创科技有限公司 Automatic casting processing method and system for resin words

Similar Documents

Publication Publication Date Title
CN112819772B (en) High-precision rapid pattern detection and recognition method
WO2021129569A1 (en) Human action recognition method
CN106530347B (en) Stable high-performance circle feature detection method
CN102156996B (en) Image edge detection method
CN113034399A (en) Binocular vision based autonomous underwater robot recovery and guide pseudo light source removing method
WO2017193414A1 (en) Image corner detection method based on turning radius
CN111354047B (en) Computer vision-based camera module positioning method and system
CN115841434A (en) Infrared image enhancement method for gas concentration analysis
CN112085651B (en) Automatic shock wave detection and tracking algorithm based on image self-adaptive threshold and feature extraction
CN109064479B (en) Sea-sky-line detection method based on gray dynamic features of adjacent video frames
CN113052794A (en) Image definition recognition method based on edge features
CN107993219A (en) A kind of deck of boat detection method of surface flaw based on machine vision
CN111429372A (en) Method for enhancing edge detection effect of low-contrast image
CN114332079A (en) Plastic lunch box crack detection method, device and medium based on image processing
CN117853510A (en) Canny edge detection method based on bilateral filtering and self-adaptive threshold
CN113781523A (en) A football detection and tracking method and device, electronic equipment and storage medium
CN118552549A (en) Transmission shaft part defect detection method and system based on image processing
CN116935496B (en) Electronic cigarette smoke visual detection method
CN110501339B (en) Cloth cover positioning method in complex environment
CN117876353A (en) Electronic equipment surface scratch detecting system based on visual recognition
CN112489052A (en) Line structure light central line extraction method under complex environment
CN115601301B (en) Method, system, electronic device and storage medium for measuring fish phenotypic characteristics
CN113643290B (en) Straw counting method and device based on image processing and storage medium
CN114067122B (en) Two-stage binarization image processing method
CN114820718A (en) Visual dynamic positioning and tracking algorithm

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20210629

WD01 Invention patent application deemed withdrawn after publication