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

Image recognition system and method based on characteristic extracting and categorizer

A feature extraction and classifier technology, applied in the field of image recognition, can solve the problem of low reliability of image recognition, and achieve the effect of strong scalability and improved reliability.

Inactive Publication Date: 2008-05-14
VIMICRO CORP
View PDF0 Cites 55 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] It can be seen that the reliability of existing image recognition based on single feature extraction and single classifier is not high

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 recognition system and method based on characteristic extracting and categorizer
  • Image recognition system and method based on characteristic extracting and categorizer
  • Image recognition system and method based on characteristic extracting and categorizer

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0058] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and examples.

[0059] FIG. 2 is a schematic structural diagram of the face recognition system based on feature extraction and classifier of the present invention. As shown in Figure 2, taking face recognition as an example, the system includes: feature extraction modules of multiple categories corresponding to different categories of features, classifiers corresponding to multiple categories, multiple discriminators, a decision module, And a database (not shown in the figure).

[0060] Among them, there are m types of feature categories, and there are n feature extraction modules corresponding to each feature category, that is, a total of m×n feature extraction modules; there are n types of classifiers, and there are m classifiers corresponding to each category. That...

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 recognition system based on feature extraction and classifier and an image recognition method based on feature extraction and classifier. The present invention selects feature categories and classifiers suitable for different categories of images to be recognized through trained discriminators, so that image recognition can be applied to different environments, and through the combination of feature extraction and classifiers of multiple categories selected Perform image recognition separately, that is, effectively organize multiple feature extraction methods and multiple classifiers for image recognition, and then make comprehensive decisions based on the recognition results obtained by multiple combinations, thereby improving the reliability of image recognition results. Moreover, the present invention has no limitation on the number of categories of features and classifiers, and can arbitrarily add feature extraction modules and / or classifiers of different categories, which has strong scalability. The invention can be applied to various image recognition based on feature extraction and classifiers such as face recognition, fingerprint recognition and iris recognition.

Description

technical field [0001] The invention relates to image recognition technology, in particular to an image recognition system based on feature extraction and classifier, and an image recognition method based on feature extraction and classifier. Background technique [0002] FIG. 1 is a schematic structural diagram of an existing face recognition system based on feature extraction and classifiers. As shown in Figure 1, the system includes a feature extraction module and a classifier. [0003] The feature extraction module is used to extract the features of the corresponding category from the received face image and output it to the classifier. [0004] The classifier is configured to match and recognize the received features and samples in the database, and output the sample identifier corresponding to the matched sample as a recognition result of the corresponding face image. [0005] Among them, different types of feature extraction modules can extract different types of fe...

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): G06K9/62G06K9/00
Inventor 王俊艳黄英
Owner VIMICRO CORP
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