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

An Image Summarization Method Based on Mean Quadratic Image and Locality Preserving Projection

A technology that maintains projections and secondary images locally, and is applied in image analysis, image data processing, computer components, etc., to achieve good robustness, improve robustness, and ensure security.

Active Publication Date: 2018-01-05
广东英视科技有限公司
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Most of these existing technologies can resist some common digital processing, such as JPEG compression and low-pass filtering, but there are many shortcomings and limitations in the classification performance in terms of robustness and uniqueness.

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
  • An Image Summarization Method Based on Mean Quadratic Image and Locality Preserving Projection
  • An Image Summarization Method Based on Mean Quadratic Image and Locality Preserving Projection
  • An Image Summarization Method Based on Mean Quadratic Image and Locality Preserving Projection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0032] Such as figure 1 As shown, an image summarization method based on mean secondary image and partial preserving projection includes the following steps:

[0033] 1) Mean secondary image construction: first use bilinear interpolation to convert the input image into M×M size, for color images, convert it to YCbCr color space and take the brightness component Y to represent; then perform non-overlapping analysis on the image Block, the size of the image block is U×U, where U has a small value and can divide M, mark Q=M / U, and get Q×Q image blocks;

[0034] Calculate the average value of each image block to obtain an average image J of size Q×Q;

[0035] Randomly select N image blocks of size P×P from J. For each image block, concatenate its column elements to obtain a size P 2 ×1 vector, arrange the vectors corresponding to N image blocks, and finally get the size P 2 ×N mean secondary image S;

[0036] 2) Gabor filtering: Set the Gabor filtering of the mean secondary image S as G=...

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 summarization method based on mean value quadratic image and local preserving projection, which is characterized in that it comprises the following steps: 1) mean value quadratic image construction; 2) Gabor filtering; 3) local preserving projection processing; 4) features Compression quantization and encryption; 5) Similarity calculation. The advantages of this method are: using the strategy of two image blocks to construct the average secondary image, which effectively compresses the image data and makes the average secondary image resistant to certain rotation operations; uses the Gabor filter to process the average secondary image Filtering effectively improves the robust performance of the summary method; using local preservation projection to reduce the dimensionality of the filtering results, quantizing the variance into bits, and further realizing data compression; using the Skew tent chaotic map to perform XOR encryption on the variance bit sequence , which ensures the security of the image summary; the extracted image summary has good robustness, uniqueness and security.

Description

Technical field [0001] The invention relates to the field of computer image processing, in particular to an image summarization method based on a mean secondary image and partial preservation projection. Background technique [0002] In the era of big data, the number of digital images that people obtain is increasing. Now that images have become the largest type of big data, how to efficiently access and manage massive digital images has become a key issue in the multimedia field that needs to be resolved. At the same time, the emergence of image editing software has made various digital processing more and more convenient. It is easy for people to process images such as JPEG compression, brightness adjustment and format conversion and save the processing results as new images. Therefore, for a given image, there may be images with the same visual content but different specific data in a large number of images. Therefore, it is an important problem to quickly retrieve visually...

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): G06T7/00G06K9/62
Inventor 唐振军阮林林张显全俞春强孙容海
Owner 广东英视科技有限公司
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