Image tecognition and correlation system

An image and pixel technology, applied in the field of image recognition and related systems, can solve the problems of unsuitable reference image templates and various combinations of retrieval image scenes

Inactive Publication Date: 2001-06-27
DATACUBE
View PDF1 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

One approach is to simply accumulate a fixed number of points in the sparse set of pixels, however, su...

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 tecognition and correlation system
  • Image tecognition and correlation system
  • Image tecognition and correlation system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] Digital image matching as defined in the present invention includes pattern matching of pixels of a reference image template to pixels of a search image scene to find similar grayscale patterns and relative positions. The correlation of these two images at a given pixel generates a correlation score indicating the degree of match between 0.0 and 1.0, where 1.0 is a perfect match. Since the reference template image to be found may be translated, rotated, scaled, deformed (perspective) or otherwise transformed in the retrieved image scene, such a correlation may not yield a perfect 1.0 score, even for the correct identification.

[0046] The defined properties of the reference image template are used to indicate the strength of the template as a matching candidate. Certain features favor high accuracy of recognition. Referring to Figure 1a, a poor formwork 10 is shown having many vertical sides and few horizontal sides. The template will be found with higher accuracy i...

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

A system for digital image recognition which combines sparse correlation with image pyramiding to reduce the number of pixels used in correlation provides effective recognition of a reference image template (100) without exhaustive correlation of all pixels in the reference image template (100). An optimal sparse pixel set (112) is selected from the pixels of the reference image template (100) by correlating the reference image template (100) against a search image scene (102) which is to be searched. Such a sparse pixel set includes those pixels which are optimal in defining the correlation sensitive features of the reference image template (100). By terminating the accumulation of sparse pixels at an optimal point, performance is maximized without compromising accuracy of recognition. The resultant optimal sparse pixel set is then correlated against the pixels in the search image scene through a series of transformations to find a match of the reference image template (100) within the search image scene (102).

Description

[0001] Cross References to Related Applications [0002] This application claims the benefit of U.S. Provisional Application No. 60 / 085,862, filed May 18, 1998, entitled "VS FIND TOOL," under U.S.C. 119(e). [0003] Statement Regarding Federally Sponsored Research or Development [0004] not applicable Background of the invention [0005] Known digital image recognition systems attempt to locate the position of a digital reference image template within a larger digital search image scene. These digital images consist of a sequence of pixels arranged in a matrix, where a gray value is derived from each pixel to represent its appearance. Matching is then performed by comparing the grayscale values ​​relative to their positions in both the digital reference image template and the digital search image scene. A match is found when the same or similar pattern as in the digital reference image template is found in the digital search image scene. [0...

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): G06T7/00G06K9/64G06K9/68
CPCG06K9/6857G06K9/6203G06V10/7515G06V30/2504G06F18/00
Inventor 斯瓦米·马尼克恩斯科特·罗思托马斯·布什曼
Owner DATACUBE
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