Super pixel Gaussian filtering pre-processing method based on JND factor

A Gaussian filtering and super-pixel technology, applied in image data processing, image communication, image enhancement, etc., can solve the problems of different smoothness and texture complexity, different sensitivity, and subjective quality degradation

Inactive Publication Date: 2015-10-21
PEKING UNIV SHENZHEN GRADUATE SCHOOL
View PDF3 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the sensitivity of the human eye to each area in the entire image is different, and the smoothness and texture complexity of each area are also diffe...

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
  • Super pixel Gaussian filtering pre-processing method based on JND factor
  • Super pixel Gaussian filtering pre-processing method based on JND factor
  • Super pixel Gaussian filtering pre-processing method based on JND factor

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] It should be noted that, in the case of no conflict, the embodiments in the present application and the features in the embodiments can be combined with each other. The present invention will be further described in detail below in conjunction with the drawings and specific embodiments.

[0028] The implementation of the preprocessing method is based on a JND factor-based superpixel Gaussian filter preprocessing system, and the system includes three main modules: an image segmentation module based on SLIC superpixel (Superpixel), and a visual JDN factor Calculation module, an adaptive Gaussian filtering module based on JND factor.

[0029] The present invention provides a superpixel Gaussian filter preprocessing method based on JND factor, the main steps are as follows:

[0030] Step 1, read in video image data: read in video image data frame by frame for processing;

[0031] Step 2. Superpixel division: using a method based on SLIC superpixel (Superpixel) to divide th...

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 super pixel Gaussian filtering pre-processing method based on a JND factor, comprising the following steps: video image data reading-in; super pixel classification: segmenting an image into super pixels which are of a predetermined size and are composed of similar pixels based on an SLIC super pixel method; JND factor calculation: calculating the visual-information-based JND factor of each pixel point in the super pixels, obtaining the average value of the JND factor, and obtaining the association between the average value and image texture and smoothness, wherein the calculated JND factor is the weighted brightness mean difference; and adaptive Gaussian filtering of the super pixels: determining the Gaussian filtering parameters of the super pixels according to the average value of the JND factor of the super pixels, and adopting the Gaussian filtering parameters to perform Gaussian filtering on the corresponding super pixels, thus obtaining a pre-processed video frame. According to the invention, a video can be adaptively filtered based on the sensitivity of the human eye to the image region, and obvious rate decline can be achieved without causing loss to subjective quality.

Description

technical field [0001] The invention relates to the field of video preprocessing, in particular to a JND factor-based superpixel Gaussian filter preprocessing method. technical background [0002] With the development of information technology, especially the development of high-definition video and mobile Internet, the number and demand of multimedia video are rapidly expanding. The development of the next-generation video coding standard HEVC has reduced the bit rate by 50% compared with the previous generation standard. It still takes a long time to develop the next-generation new video coding standard and bring it to practical applications. Processing technology can significantly improve the efficiency of video coding and improve its subjective quality. [0003] Video preprocessing technology is a series of processing operations performed on video before it is encoded. The main purpose is to reduce the bit rate and improve the quality. After years of research and devel...

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
IPC IPC(8): G06T5/00
CPCH04N19/00
Inventor 丁磊王荣刚王振宇高文
Owner PEKING UNIV SHENZHEN GRADUATE SCHOOL
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap