Unlock instant, AI-driven research and patent intelligence for your innovation.

A blurred image detection method, device and system

A fuzzy image and detection method technology, applied in the field of image processing, can solve the problems of long calculation time, low accuracy rate, high calculation complexity, etc., and achieve the effect of fast detection speed, high detection speed and accurate detection speed

Active Publication Date: 2021-09-07
XIAMEN MEET YOU INFORMATION TECH
View PDF11 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Existing image blur detection algorithms can be roughly divided into two categories: space domain and frequency domain: gradient-based algorithms are mostly used in the space domain, such as Laplace (Laplace) algorithm, difference and Sobel operator, etc. Fast, but the adaptability to changes in the image itself is not high, resulting in low accuracy in a large number of applications; in the frequency domain, the FFT transform or wavelet transform of the image is often used. The detection effect of this type of algorithm is good, but the computational complexity is high. , The calculation time is long, not suitable for real-time detection system

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A blurred image detection method, device and system
  • A blurred image detection method, device and system
  • A blurred image detection method, device and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0024] This embodiment provides as figure 1 A fuzzy image detection method is shown, comprising:

[0025] S1. Calculate the average gradient variance V of the image to be detected based on the gradient variance operator;

[0026] S2. Calculate the comprehensive contrast C of the image according to the preset comprehensive contrast formula;

[0027] S3. Process the comprehensive contrast according to a preset mapping formula to obtain a fuzzy value F;

[0028] S4. Mark the image to be detected as a blurred image or a clear image according to the blur value F and the average gradient variance V, thereby realizing blurred image detection.

[0029] Wherein, the sorting of S1 and S2 is only a specific embodiment, that is, the two (the process of calculating V and the process of calculating C) can be performed at the same time, or one of them can be performed first.

[0030] Wherein, the gradient variance operator is specifically:

[0031] Among them, P i,j is the pixel to be...

Embodiment 2

[0042] The purpose of this embodiment is to explain the actual application scenario of the present invention to illustrate the technical application purpose and technical application effect.

[0043] As mentioned in the background, the clarity of an image or video can affect a user's viewing experience. The amount of information in today's society is gradually expanding, and it is difficult to process and judge a large amount of image data by manpower alone. Therefore, it is necessary to use a computer to identify and mark image blur, and the corresponding derivative application can be Such as figure 2 The blurry image exclusion process shown:

[0044] S00, inputting / acquiring several images to be detected;

[0045] S01. Calculate the comprehensive contrast C of the image according to the preset comprehensive contrast formula;

[0046] S02. Process the image to be detected based on the gradient variance operator to obtain the average gradient variance V of the image;

[0...

Embodiment 3

[0052] This embodiment provides as image 3 The blurred image detection device shown includes:

[0053] Variance calculation module 1, for calculating the average gradient variance V of the image to be detected based on the gradient variance operator;

[0054] The contrast calculation module 2 is used to calculate the comprehensive contrast C of the image according to the preset comprehensive contrast formula;

[0055] A fuzzy value calculation module 3, configured to process the comprehensive contrast according to a preset mapping formula to obtain a fuzzy value F;

[0056] The judging module 4 is configured to mark the image to be detected according to the fuzzy value F and the average gradient variance V.

[0057] This embodiment provides a blurred image detection system, which includes at least one processor, and the processor is configured to execute the above method.

[0058] This embodiment provides a computer-readable storage medium, where the computer-readable storag...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a fuzzy image detection method, device and system. The method includes: calculating the average gradient variance V of an image to be detected based on a gradient variance operator; calculating the comprehensive contrast C of the image according to a preset comprehensive contrast formula; The mapping formula processes the comprehensive contrast to obtain a fuzzy value F; and marks the image to be detected according to the fuzzy value F and the average gradient variance. Apparatus and systems are used to perform the methods. The embodiment of the present invention obtains the average gradient variance V of the image based on the gradient variance operator, calculates the comprehensive contrast C according to the contrast formula, processes the average gradient variance and the comprehensive contrast according to the mapping formula to obtain the fuzzy value F, and marks the image to be detected according to the fuzzy value F and the threshold value The image can judge the blur degree of the image by combining the image gradient and the comprehensive contrast, so that the blur image detection speed is fast and accurate.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a fuzzy image detection method, device and system. Background technique [0002] Images and videos are excellent ways to obtain information. The display quality of images and videos will affect the user's viewing experience. Therefore, eliminating abnormal images can improve the user's viewing experience. When processing a large number of images, it is very unreasonable to rely solely on manual recognition , image processing is the current mainstream method for image blur detection. [0003] Existing image blur detection algorithms can be roughly divided into two categories: space domain and frequency domain: gradient-based algorithms are mostly used in the space domain, such as Laplace (Laplace) algorithm, difference and Sobel operator, etc. Fast, but the adaptability to changes in the image itself is not high, resulting in low accuracy in a large number of application...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06T7/00
CPCG06T7/0002G06T2207/30168
Inventor 陈方毅黄容鸿
Owner XIAMEN MEET YOU INFORMATION TECH