Improving performance of image recognition algorithms by pruning features, image scaling, and spatially constrained feature matching

A technology for querying images and feature matching, applied in character and pattern recognition, instrumentation, computing, etc., can solve problems such as slow convergence rate

Inactive Publication Date: 2012-10-31
QUALCOMM INC
View PDF3 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, as the ratio of inner to exposed layers decreases, the RANSAC algorithm becomes exponentially slower (i.e., slower convergence rate)

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
  • Improving performance of image recognition algorithms by pruning features, image scaling, and spatially constrained feature matching
  • Improving performance of image recognition algorithms by pruning features, image scaling, and spatially constrained feature matching
  • Improving performance of image recognition algorithms by pruning features, image scaling, and spatially constrained feature matching

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] Various embodiments are now described with reference to the drawings, wherein like reference numerals are used to refer to like elements throughout. In the following description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of one or more embodiments. It may be evident, however, that such embodiments may be practiced without these specific details. In other instances, well-known structures and devices are shown in block diagram form in order to facilitate describing one or more embodiments.

[0047] overview

[0048] Various features described herein relate to improving the speed and / or efficiency of image recognition.

[0049] According to a first aspect, keypoints in a query image are grouped into clusters. Keypoints from the query cluster are matched to the target cluster based on a high correspondence threshold. Query keypoints that satisfy the threshold (or better) are full matches and are con...

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 method for feature matching in image recognition is provided. First, image scaling may be based on a feature distribution across scale spaces for an image to estimate image size/resolution, where peak(s) in the keypoint distribution at different scales is used to track a dominant image scale and roughly track object sizes. Second, instead of using all detected features in an image for feature matching, keypoints may be pruned based on cluster density and/or the scale level in which the keypoints are detected. Keypoints falling within high-density clusters may be preferred over features falling within lower density clusters for purposes of feature matching. Third, inlier-to-outlier keypoint ratios are increased by spatially constraining keypoints into clusters in order to reduce or avoid geometric consistency checking for the image.

Description

[0001] Claim of priority under 35 U.S.C. §119 [0002] The title of this patent application claimed on December 2, 2009 is "Improving Local Feature Classifier Performance and Efficiency and Convergence Rate of RANSAC by Using Key Point Clustering Method" RANSAC by Using a Keypoint Clustering Method), which is assigned to the assignee of the present invention and is hereby incorporated by reference herein. technical field [0003] One feature relates to computer vision, and more particularly, to methods and techniques for improving the performance, efficiency, and reducing the computational complexity of image recognition techniques. Background technique [0004] Various applications would benefit from having a machine or processor capable of recognizing objects in a visual representation (eg, an image or picture). The field of computer vision attempts to provide techniques and / or algorithms that permit the recognition of objects or features in images, where the objects or ...

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): G06K9/64
CPCG06K9/6211G06V10/757G06V10/40
Inventor 桑迪普·瓦达迪约翰·H·洪奥努尔·C·哈姆西奇尤里娅·列兹尼克重·U·李
Owner QUALCOMM INC
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