Object type identification method combining plurality of interest point testers

An interest point detection and interest point technology, applied in the fields of image understanding, computer vision, and pattern recognition, can solve problems such as poor robustness, complex model, and excessive supervision, achieving good average effect, simple practice, and reduced supervision. Effect

Inactive Publication Date: 2012-07-25
JIANGXI UNIV OF SCI & TECH
View PDF2 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] In order to solve the problems of overly complex models, overly strong supervision and poor robustness in traditional object class recognition, the present invention provides a method for using dictionary collectives to parallelly utilize multiple information existing in images to identify object classes

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 type identification method combining plurality of interest point testers
  • Object type identification method combining plurality of interest point testers

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment

[0038] Resize the images so that each image contains approximately 40,000 pixels (aspect ratio preserved). Because the SIFT descriptor is the most popular and effective descriptor, and most existing related methods use 128-dimensional SIFT vectors to describe interest points. So preferred embodiments also use it to delineate points of interest. Each time 60% of the images are selected to form a new training subset. 60 interest points are randomly selected from each image, and k-means is used to construct a visual dictionary of members. Because of the inherent randomness of the k-means algorithm, it is equivalent to using different clusterers when forming different member dictionaries. In most studies related to the “bag-of-words” model, the size of the visual dictionary is between 100 and 1000, so this parameter is set to a middle value of 500. Linear SVM (Support Vector Machine) learns a classifier based on the quantized vector set of each member dictionary. This process ...

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 field of mode identification, computer vision and image understanding and discloses an object type identification method combining a plurality of interest point testers. The method disclosed by the invention comprises the following steps of: firstly, extracting an interest point containing various shapes, edge outline and gray information through different interest point testers, so as to form different expression vectors of an image. A visual dictionary set can be obtained based on different interest point sets, and each member utilizes one different image characteristic. A classifier set is obtained based on the generated visual dictionary set, so as to create an object type cognitive model and a model learning method to adapt to the selecting characteristics according to the current identification task. As shown in a test, the method can combine information detected by different interest point testers and capture different characteristics of the image so as to effectively improve the performance of the traditional object type identification method based on a single visual dictionary.

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 object class recognition method. Background technique [0002] Object class recognition is a key problem in the field of computer vision. Object class models must handle the balance between intra-class variation and inter-class similarity. Humans can easily recognize many object classes, but for computers and robots, this task is extremely challenging. At the object class level, changes in lighting conditions, geometric deformations, occlusions, and background noise all pose many challenges for effective learning and robust recognition. In addition, object class recognition has to overcome the great differences between different instances within the class. [0003] An image contains a lot of information, how to characterize an image so that it can be effectively and efficiently used for recognition. This pro...

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): G06K9/62
Inventor 罗会兰井福荣张彩霞
Owner JIANGXI UNIV OF SCI & TECH
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