Invariance recognition method based on visual vocabulary book collection

A visual vocabulary and recognition method technology, applied in the field of invariant recognition, can solve the problems of complex models, poor robustness, and excessive supervision, and achieve the effect of simple models, low requirements, and low supervision.

Inactive Publication Date: 2012-08-22
FUDAN UNIV
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0010] In order to solve the problems of overly complex models, overly strong supervision and poor robustness in traditional object recognition, the present invention provides a method for using a vocabulary collective to parallelly utilize multiple information existing in images to identify objects

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
  • Invariance recognition method based on visual vocabulary book collection
  • Invariance recognition method based on visual vocabulary book collection
  • Invariance recognition method based on visual vocabulary book collection

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment

[0036] First randomly sample 60% of the training data, and then on this sampled data set, for each training image, first use the 'canny' edge detector to detect the edge of the image, and randomly sample m points on the detected edge ( Such as 60 points), these points are used as the center points to extract n×n (such as 16×16) pixel-sized blocks as the interest points of this image, and then the following 8 descriptors are used to describe the sampled interest points:

[0037] (1) Color descriptor: the color value of each pixel in the interest point is used to form an n×n×3-dimensional feature vector (such as 16×16×3=768 dimensions), and this type of descriptor is used to capture The color information of the image.

[0038] (2) Color wavelet descriptor: The color information of each point of interest is decomposed by 'Haar' two-dimensional wavelet first-order to obtain n×n×3-dimensional feature vectors. This type of descriptor can incorporate multi-resolution information of ...

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 belongs to the technical fields of pattern recognition, computer vision and image understanding, in particular to an invariance recognition method based on a visual vocabulary book collection. Firstly, training data are sampled, and then interest points are sampled, the interest points are described by using different feature describing methods, and the described vectors are clustered to establish a visual vocabulary book. By utilizing different data subcollections and interest point subcollections obtained by each sampling and different feature describing methods, the visual vocabulary book collection is obtained. A classifier collection is obtained on the basis of the generated visual vocabulary book collection, thus establishing a cognitive model of an object class and a learning method of the model and enabling the object class to select the feature or the feature weight self-adaptively according to the current recognition task. Experiment results show that the method has better effect and can effectively improve the performance of the traditional image recognition method based on a single visual vocabulary book collection.

Description

technical field [0001] The invention belongs to the technical fields of pattern recognition, computer vision and image understanding, and in particular relates to an invariance recognition method. Background technique [0002] The current challenge of computer vision is invariance recognition, which has become a hot research topic of many experts and scholars. Invariant recognition refers to the ability to accurately recognize objects when the viewing angle, scale, and lighting conditions change, or when there is occlusion, background noise, or a certain degree of deformation. The existing research methods mainly include: [0003] 1. Global shape-based methods. In order to achieve invariant recognition, many early works, typically in [1], applied geometric methods to extract edge contours to represent objects. This representation is invariant to lighting and makes the decision of 2D or 3D pose relatively simple. But this method relies on the object contour, they assume t...

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 Patents(China)
IPC IPC(8): G06K9/66
Inventor 危辉罗会兰
Owner FUDAN 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

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