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

Context-based local spatial information modeling method

A technology of local space and modeling method, which is applied in the field of pattern recognition to achieve the effect of improving classification accuracy

Inactive Publication Date: 2013-02-27
INST OF AUTOMATION CHINESE ACAD OF SCI
View PDF1 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Therefore, given that algorithms that only consider absolute spatial information can no longer meet practical needs, we propose a method based on the context of local features to process local spatial information in images

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
  • Context-based local spatial information modeling method
  • Context-based local spatial information modeling method
  • Context-based local spatial information modeling method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0026] In order to describe the specific implementation of the present invention in detail, a scene classification data set is taken as an example. The dataset contains more than 4000 images showing 15 different scenes. The implemented system can give the category label of the scene displayed by the image according to the content of the image. Specific steps are as follows:

[0027] 100 images are randomly selected from each type of scene to form a training image set. All remaining images constitute the test set.

[0028] Step S1, extracting SIFT local features from all images in a dense sampling manner.

[0029] In step S2, 1 million local features are randomly extracted from the training set, and a visual dictionary containing 1024 visual words is learned by using the k-nearest neighbor clustering algorithm.

[0030] Step S3, extract the surrounding area of ​​each local feature as its context area, and obtain the context feature by hard voting on the visual dictionary ob...

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 a context-based local spatial information modeling method which comprises the steps of extracting corresponding context characteristics after extracting local characteristics of each image; extracting local characteristic groups randomly from an test image according to a visual word corresponding to each local characteristic; training on the context characteristic set corresponding to each group of local characteristics to obtain groups of context modes by clustering algorithm; and gathering different context modes corresponding to the local characteristics and connecting the gathering results to obtain the final expression of the image. The method still can effectively handle the spatial information for images which are not aligned. In actual application, the method is combined with current methods taking absolute space relationship into consideration, so that the image classifying precision is further improved.

Description

technical field [0001] The present invention relates to pattern recognition, in particular to image classification based on BoF (bag-of-features) model Background technique [0002] At present, traditional classification algorithms lack the ability to effectively express the spatial information of images. This is also one of the important reasons why there is still a huge gap in recognition accuracy between the computer vision system and the human vision system. Common image space modeling methods can only deal with absolute space information, for example, pyramid space matching algorithm. Such algorithms often rely on the bias of the data set to work, and are only effective for aligned images, and even completely ineffective for images with large offsets. [0003] Therefore, given that algorithms that only consider absolute spatial information can no longer meet practical needs, we propose a method based on the context of local features to process local spatial informatio...

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 谭铁牛黄永祯王亮吴子丰
Owner INST OF AUTOMATION CHINESE ACAD OF SCI
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