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

Object recognition method based on surf

An object recognition and object technology, applied in the field of object recognition, can solve problems such as the recognition rate needs to be improved, the calculation is complex and time-consuming, and the invariant moment is poor in robustness.

Inactive Publication Date: 2014-08-27
HENAN UNIV OF SCI & TECH
View PDF2 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Literature [4] (Li Yingchun, Chen Hexin, Zhao Ming. Research on Affine Invariant Moment Based on Aircraft Target[J]. Journal of Jilin University, 2003, 21(5): 84-88) used the third-order affine invariant moment For aircraft identification, this method is very effective for the identification of distorted aircraft, but due to the poor robustness of invariant moments, it is less used now
Literature [7] (Shengnan Sun, Shicai Yang, Lindu Zhao.Noncooperative bovine iris recognition via SIFT[J].Neurocomputing,2013,1-8) used the SIFT algorithm to realize the iris recognition of cattle. The algorithm has high stability, but due to the data The amount is large, the calculation is more complicated and time-consuming
Literature [8] (Zhou Xinyu, Yao Maoguo, Zhu Leqing. Research on palmprint recognition technology based on SURF algorithm and openCV [J]. Journal of Hangzhou Dianzi University, 2012, 32, (3): 45-49) using the surf algorithm to extract effective The feature points in the palmprint area are matched by random sampling consensus algorithm. This method has better robustness, but the recognition rate needs to be improved

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
  • Object recognition method based on surf
  • Object recognition method based on surf
  • Object recognition method based on surf

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] (1) SURF feature vector extraction method

[0040] In the SURF feature extraction algorithm, after an object undergoes illumination changes, scale transformations, rotation transformations, and noise changes, one of the frontal images is selected from the multiple images captured as the standard image, and the other images are used as images to be recognized.

[0041] A fast Hessian detector is first used to detect interest points (extreme points) on the image. Hessian matrix H by the function f ( x , y ), whose general definition is shown in formula (1). H The matrix discriminant is defined as shown in formula (2). The discriminant value is H eigenvalues ​​of the matrix 。 By introducing the scale space theory, in the scale The Hessian matrix on is defined as formula (3), where , with is on point The convolution result of the image at place and the corresponding 2nd-order Gaussian template. In order to reduce the amount of calculation, the SURF algo...

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 relates to an object recognition method based on surf. According to the method, a feature vector set is set up by using SURF of multiple images of an object undergoing illumination, size, rotation and noise changes, the feature vector set is matched with a feature vector set of a standard image, and then a final recognition result is determined by adopting a weight similarity product method. The object recognition method is high in recognition rate, and robustness of the object recognition method is verified.

Description

technical field [0001] The invention relates to object recognition, in particular to an object recognition method based on surf features. Background technique [0002] Object recognition is an important research direction in the field of pattern recognition and computer vision, and is widely used in industrial inspection, medical analysis, robot grabbing workpieces, automatic navigation, automatic detection, etc. At present, a large number of researchers and scholars have invested a lot of manpower and material resources in this research, and put forward a variety of theories and methods. In general, object recognition methods can be divided into two categories: object recognition algorithms based on global features and object recognition algorithms based on local features. The former extracts the global features of the object, and then combines algorithms such as support vector machines and neural networks for recognition. This type of method can successfully identify noi...

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): G06K9/00
Inventor 张蕾董永生白秀玲张明川普杰信邝涵菲
Owner HENAN UNIV OF SCI & TECH
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