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

Variance ratio feature based image fuzzy region detection and fuzzy core calculation method

A technology of fuzzy area and calculation method, applied in the field of computer vision, to achieve the effect of simple program and easy implementation

Inactive Publication Date: 2016-05-11
TIANJIN UNIV
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although this algorithm can get a better deblurring effect, it needs to manually calibrate the rectangular block and set the direction of the blur kernel.

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
  • Variance ratio feature based image fuzzy region detection and fuzzy core calculation method
  • Variance ratio feature based image fuzzy region detection and fuzzy core calculation method
  • Variance ratio feature based image fuzzy region detection and fuzzy core calculation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0054] Based on the proposed variance ratio feature, the present invention distinguishes blurred areas and clear areas of images by training an SVM classifier, thereby performing blurred area detection. And use the variance ratio to match the fuzzy kernel, and calculate the fuzzy kernel of the fuzzy area. In this process, it mainly includes two parts, namely, fuzzy area classification and fuzzy kernel calculation. The specific implementation method is as follows:

[0055] 1) SVM classifier for fuzzy area detection

[0056] 11) Select a training image set, one part is the image blurred by the blur kernel k, and the other part is the clear image.

[0057] 12) Block the training image and extract its variance ratio feature vector z k .

[0058] 13) Train a linear SVM classifier:

[0059] g k ( z k ) = w k ...

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 relates to a variance ratio feature based image fuzzy region detection and fuzzy core calculation method. The method comprises the steps of classifying a fuzzy region and a clear region of an image by training an SVM classifier to detect the fuzzy region; and performing fuzzy core matching through a variance ratio to calculate a fuzzy core of the fuzzy region. According to the method, better fuzzy region detection and fuzzy core calculation can be realized.

Description

technical field [0001] The invention belongs to the field of computer vision, and relates to a method for blur region detection and blur kernel calculation in an image deblurring process. Background technique [0002] Since the rise of computer technology, digital image technology has been widely used in various fields such as military affairs, people's livelihood, and education. However, in daily life, due to various reasons such as weather, light, equipment, etc., the pictures we take will become blurred. The appearance of blurred images will make us unable to accurately distinguish objects in the image, and in severe cases, we will lose some important information. Blurred images take on different shapes depending on what causes them to form. For example, the out-of-focus blur caused by the camera not focusing, or the motion blur caused by the movement of objects in the scene under insufficient light conditions. [0003] Image deblurring technology refers to the algorit...

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
CPCG06T7/0002G06T2207/20024G06T2207/30168
Inventor 周俊庞彦伟
Owner TIANJIN UNIV