Increment neural network and sub-graph code based image classification method

A technology of neural network and classification method, applied in the field of image classification

Inactive Publication Date: 2013-05-22
NANJING UNIV
View PDF4 Cites 27 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although many researchers at home and abroad have devoted themselves to the research of ...

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
  • Increment neural network and sub-graph code based image classification method
  • Increment neural network and sub-graph code based image classification method
  • Increment neural network and sub-graph code based image classification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0055] This embodiment is divided into a training phase and a classification phase, and the main processes of each embodiment part are introduced below:

[0056] Training phase process:

[0057] 1. Local feature extraction: Local feature extraction is performed on a set of training image sets I. The local feature descriptor can effectively represent the local information of the image, which provides the basis for forming the subsequent overall image description. The present invention uses SIFT feature as the local feature of the image. In addition, when extracting local features of the image, it is also necessary to determine the sampling strategy, that is, dense sampling or sparse sampling (interest point sampling). These two sampling methods are divided by the number of sampling points in an image. If only some interest points of an image are sampled and the number of sampling points is relatively small, it is called sparse sampling; Widely extracting sampling points from ...

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 discloses an increment neural network and sub-graph code based image classification method. The increment neural network and sub-graph code based image classification method comprises the following steps of: extracting local characteristics; studying increment code books in a network; performing characteristic coding based on a sub-graph; getting image spaces together; and studying a classifier and predicting a model. The increment neural network and sub-graph code based image classification method greatly reduces time complexity of a traditional algorithm to a great extent as the code book can be studied efficiently, and the space relationship between visual words is also kept; in addition, the characteristic coding based on the sub-graph is specifically for performing characteristic coding by fully utilizing the space relationship between the visual words, so that more abundant semantic information can be extracted, and excellent classification performances are obtained finally while the computational efficiency of a classification system is increased. Therefore, the increment neural network and sub-graph code based image classification method has a relatively high use value.

Description

technical field [0001] The invention belongs to the field of image classification, in particular to an image classification method based on incremental neural network and subgraph coding. Background technique [0002] In the current information society, digital media resources represented by images have reached a massive scale and become the main body of current information processing and information resource construction. Traditional technical means have been unable to meet this demand, which poses new challenges to technologies such as image organization, analysis, retrieval and management. Image classification, as the basic technology for machine understanding of images, has been a continuous frontier research hotspot in many important research fields such as pattern recognition, computer vision, information retrieval, artificial intelligence, machine learning and data mining in recent years. Image classification refers to the method of classifying images into specific s...

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): G06K9/66
Inventor 杨育彬唐晔潘玲燕
Owner NANJING 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