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

Ambiguity judging method and system of image block

A technology of image blocks and blurriness, applied in the field of image processing, can solve the problems that the detection accuracy is easily affected by image blur, missing detection, multiple detection, etc., and achieve the effect of simplicity, practicality and efficiency

Inactive Publication Date: 2015-05-27
PEKING UNIV +2
View PDF5 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method generally requires edge extraction, which requires a large amount of calculation, and the detection accuracy is easily affected by image blur.

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
  • Ambiguity judging method and system of image block
  • Ambiguity judging method and system of image block
  • Ambiguity judging method and system of image block

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0068] In this embodiment, the blurriness threshold is defined as 17, and an image with a blurriness less than 17 is blurred, and an image greater than or equal to 17 is clear. The normalized size of the image is 60×60, and the normalized range of brightness is 0-255.

[0069] Figure 3a is the image block to be processed in this embodiment, Figure 3b is the image after size normalization and brightness normalization, Figure 3c is the binary image after binarization.

[0070] First, extract Figure 3c The skeleton of the binary image shown, and calculate the distance of all pixels in the image and the skeleton, namely seek distance transformation, then set up the gray level-distance histogram, the histogram among the present embodiment is as Figure 4 shown. Afterwards, the slope of the longest rising slope in the histogram is taken as the blurriness. In this embodiment, the slope of the longest rising slope is 10.95. Since it is smaller than the blurriness threshold, t...

Embodiment 2

[0072] In this embodiment, the blurriness threshold is defined as 17, and an image with a blurriness less than 17 is blurred, and an image greater than or equal to 17 is clear. The normalized size of the image is 60×60, and the normalized range of brightness is 0-255.

[0073] Figure 5a is the image block to be processed in this embodiment, Figure 5b is the image after size normalization and brightness normalization, Figure 5c is the binary image after binarization.

[0074] First, extract Figure 5c The skeleton of the binary image shown, and calculate the distance of all pixels in the image and the skeleton, promptly seek distance transformation, then set up gray scale-distance histogram, the histogram among the present embodiment is as Image 6 shown. Afterwards, the slope of the longest rising slope in the histogram is taken as the ambiguity. In this embodiment, the slope of the longest rising slope is 28. Since it is greater than the ambiguity threshold, the image...

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 an ambiguity judging method and system of an image block. The ambiguity judging method comprises the following steps: firstly, binarizing a to-be-processed image block, extracting a framework of the processed binarized image block, calculating distances between all pixel points in the image block and the framework, establishing a gray level-distance histogram by using the distances as a horizontal axis and gray level values of the pixel points as a longitudinal axis; finally, calculating a slope of the longest ascending ramp in the gray level-distance histogram, and using the slope as ambiguity of the to-be-processed image block, and indicating that the smaller the slope is, the more obscure the image block is. According to the method and the system, through establishing the gray level-distance histogram, a foreground image framework in the image is outwards enlarged when being used as a basic shape, a conversion condition of an edge pixel gray level average value of the enlarged shape is used for analyzing the length, namely, the definition, of an image edge transition belt, so that the ambiguity of the image can be rapidly judged without accurately positioning a boundary of the image, therefore, the ambiguity judging method is simple and practical, and is high in efficiency.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a method and system for judging the blurriness of an image block. Background technique [0002] Blurred images generally manifest as unclear image structures. Most of the current image blur judgment methods require a reference image to assist in judging the clarity of the image. This method is obviously not practical. It is more practical to judge whether the structure is clear by analyzing the length of the transition zone on the inner edge of the image without using the image clarity evaluation method of the reference image. [0003] The image clarity evaluation method that does not require a reference image generally judges whether the image is clear by analyzing the width of the inner edge of the image. The general process is to first detect the boundary of the image, and then analyze the boundary width. For example, near the detected boundary point, find the local ...

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 Applications(China)
IPC IPC(8): G06T7/00
CPCG06T7/0002
Inventor 李平立刘文王建华史培培王思萌
Owner PEKING UNIV