Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Image compression method based on active learning and semi-supervised learning

A semi-supervised learning and active learning technology, applied in image coding, image data processing, instruments, etc., can solve the problem of not satisfying the objective function of the optimal decoding process, and achieve the effect of shortened time and optimal compression rate

Inactive Publication Date: 2014-03-05
ZHEJIANG UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The previous method is to directly generate representative pixels through the NCut algorithm, but these representative pixels do not meet the objective function of the optimal decoding process

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
  • Image compression method based on active learning and semi-supervised learning
  • Image compression method based on active learning and semi-supervised learning
  • Image compression method based on active learning and semi-supervised learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0017] see figure 1 , shows a flowchart of an image compression method based on active learning and semi-supervised learning in the present invention. The detailed implementation steps are as follows:

[0018] 1. Given a picture, extract the spatial position, gray value and color information (YUV space) of each pixel as a feature value; divide it into several rectangular areas on average according to the size of the image, and in each rectangular area Randomly select a pixel to form a matrix X of pixels to be selected; and construct a k-nearest neighbor graph S according to the spatial positions of these points, when x i is x j neighbors or x j is x i When the nearest neighbor of S, the element S in S ij =1.

[0019] 2. This method only stores the position and gray value of all pixels when compressing the image, and selects a part of the pixel Z to record its color value at the same time, and uses Z to learn a linear regression model when decompressing Then use this to...

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 image compression method based on active learning and semi-supervised learning, which selects color information of some representative pixel points in an image to learn a model which can predict colors of the remaining pixel points in the image on the basis of the active learning. The image compression method mainly includes the following steps that all pixel points of the image are provided, the image is segmented into a plurality of rectangular areas simply, one pixel point is respectively and randomly selected from each rectangular area, the pixel points are learned actively so as to select the most representative pixel points, grey level values and color values of the most representative pixel points are recorded, grey level values of the remaining pixel points of the image are only recorded, and a compression process is completed. During decompression, Laplace regularized least squares (LapRLS) serving as a semi-supervised learning algorithm is used for predicting and restoring colors of all pixel points.

Description

technical field [0001] The invention relates to the technical field of image compression in machine learning, in particular to an image compression method based on active learning and semi-supervised learning. Background technique [0002] Most images have a common feature: neighboring pixels are correlated, so the image contains redundant information. The goal of image compression is to reduce the redundancy of images so that images can be stored in an efficient form. A typical image compression algorithm first transforms the image from the time domain to the frequency domain through some transformation techniques, such as discrete cosine transform and discrete wavelet transform; and then encodes the transform coefficients. The mainstream image compression mechanism based on signal processing has a common structure, which is to perform information entropy coding after transformation. [0003] Recently, machine learning techniques have been applied to image compression and...

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): G06T9/00
Inventor 何晓飞卜佳俊陈纯周宇
Owner ZHEJIANG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com