Image retrieval and filter apparatus based on image wavelet feature and method thereof

An image retrieval and wavelet feature technology, applied in special data processing applications, instruments, electrical digital data processing, etc., can solve problems such as unfavorable feature storage and matching, complex image feature forms, and inability to achieve feature rotation invariance, etc. The effect of feature simplification, reduction of storage space and matching time, and improvement of matching speed

Inactive Publication Date: 2009-08-26
SOUTHEAST UNIV
View PDF0 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The emergence of this new situation raises new questions: First, for the government and some companies, how to effectively monitor and filter these multimedia contents is an urgent and important issue related to national information security and enterprise information security. task; secondly, for the vast number of Internet users, can a fast and accurate retrieval technology be provided, so that users can retrieve the images they need in the vast network like searching for text; finally, for multimedia file copyright For the owner, can it provide a fast near duplication file retrieval strategy, so as to realize the effective protection of copyright and the rapid discovery of infringement?
[0006] However, because the coefficients of the Haar transform change with the rotation of the image, the method proposed by ImgSeek cannot achieve the rotation invariance of the feature; moreover, the image feature form proposed by Imgseek is more complicated, which is not conducive to the storage and matching of features. There is still a lot of room for improvement in storage space

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 retrieval and filter apparatus based on image wavelet feature and method thereof
  • Image retrieval and filter apparatus based on image wavelet feature and method thereof
  • Image retrieval and filter apparatus based on image wavelet feature and method thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] figure 1 is a block diagram of an apparatus for filtering or retrieving images according to a preferred example of the present invention. figure 1 The device includes: feature extraction unit 2000, matching scoring unit 2100.

[0039]The feature extraction unit 2000 first performs scale correction on the input image signal (that is, the image to be retrieved), and performs multi-level wavelet transformation on the corrected image to obtain the transformation coefficients, then performs thresholding processing on the obtained transformation coefficients and scans, and finally Get the 1D features of the image. In order to complete it, the feature extraction unit 2000 includes: a size corrector 2010 , a wavelet transformer 2020 (Haar wavelet is selected in this preferred example), and a feature extractor 2030 .

[0040] The following describes the process of the feature extraction unit in detail:

[0041] First of all, in order to prevent the image from being too large ...

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 provides an image retrieval and filter apparatus based on wavelet feature and a method thereof, relating to an image retrieval and filter method, in particular to a fast image retrieval and filter apparatus which is based on wavelet feature and has stronger invariability on operations such as rotating, noise increasing, filtering and scaling changing and the method thereof. The apparatus comprises a feature extracting unit and a match marking unit, wherein the feature extracting unit is used for carrying out tree-type structure scanning on the wavelet transformation coefficient after thresholding to effectively extracting the feature of the image, and the match marking unit is used for evaluating the matching degree of the image feature to be retrieved and the image feature in the store and outputting the marking of the matching degree. The invention realizes the aim of fastness, simplicity and unchanged rotation.

Description

technical field [0001] The invention relates to a device and method for image retrieval and filtering, in particular to a fast image retrieval and filtering device and method based on wavelet feature-based operations such as anti-rotation, noise addition, filtering, and scale change. Background technique [0002] In recent years, with the continuous development of Internet technology and multimedia technology, massive images and video files have been widely disseminated through the Internet and other electronic media. The emergence of this new situation raises new questions: First, for the government and some companies, how to effectively monitor and filter these multimedia contents is an urgent and important issue related to national information security and enterprise information security. task; secondly, for the vast number of Internet users, can a fast and accurate retrieval technology be provided, so that users can retrieve the images they need in the vast network like ...

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): G06F17/30G06K9/36G06K9/46
Inventor 王桥姚伟峰王川凌苗
Owner SOUTHEAST UNIV
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