Image content retrieval system and image content sparse learning method thereof

A technology of image content and retrieval system, applied in special data processing applications, instruments, electronic digital data processing, etc., can solve the problem that image semantic information cannot be fully and effectively expressed, and achieve the effect of easy programming

Inactive Publication Date: 2013-07-31
NANJING LONGYUAN MICROELECTRONICS TECH CO LTD
View PDF1 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The technical problem to be solved by the present invention is that the existing image cont

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
  • Image content retrieval system and image content sparse learning method thereof
  • Image content retrieval system and image content sparse learning method thereof
  • Image content retrieval system and image content sparse learning method thereof

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0015] The present invention will be further described below in conjunction with the accompanying drawings.

[0016] like Figure 1-2 As shown, in multi-instance learning, each sample is composed of a set of unlabeled feature vectors, each feature vector is called an example, and a labeled sample composed of a set of examples is called a bag. The problem is described as follows: Assume that each data in the training set is a bag (Bag, that is, a sample), each bag is composed of multiple examples, each training bag has a concept label, but the example has no concept label. If at least one example in a bag is positive, the bag is marked as positive; if none of the examples in the bag is positive, the bag is marked as negative. The learning system learns the training set composed of multiple packages to predict the concept labels of packages outside the training set as correctly as possible. When using multi-instance learning in CBIR, the image must first be represented as a mu...

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 image content retrieval system which is characterized by comprising 1) a segmentation subsystem, 2) an image area characteristic extraction unit and 3) a calculation and comparison subsystem, wherein the segmentation subsystem is used for respectively segmenting the training image and testing image into n examples and comprises A) an FCM segmentation unit and B) a pyramid segmentation unit, wherein the FCM segmentation unit is used for respectively performing area segmentation on the training image and the testing image by employing a fuzzy C-means and the pyramid segmentation unit is used for performing image segmentation on the training image and the testing image on the basis of a space pyramid matching mechanism by employing a cvPrySegmentation function; the image area characteristic extraction unit is used for extracting the color, texture, CENTRIST characteristics and each type of mean characteristic vectors of each example; and the calculation and comparison subsystem adopts a multi-example learning and diverse density sparse learning method, describes the image contents from the multiple nonlocal form characteristic angles and fulfills the retrieval aim. The method is easily realized through programming, has a certain artificial intelligence and provides algorithmic reference for the image understanding.

Description

technical field [0001] The invention relates to a content-based image retrieval system and method, in particular to an image content retrieval system and an image content sparse learning method thereof. Background technique [0002] At present, the feature description of traditional image content mostly uses physical features such as color, texture, and shape to describe image content, but these features cannot fully and effectively express the semantic information of the image. At the same time, the features that describe the image content are relatively single. An image often has multiple forms, such as color, texture, shape, etc. Even for the same morphological feature, there are many different representation methods. Only using a single feature retrieval cannot effectively organize Various features reflect image content from different angles. In addition, the technology to solve the feature representation, extraction and reconstruction of high-dimensional image samples ...

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): G06F17/30G06K9/46
Inventor 宋晓宁陈勇王卫东叶华石亮范燕
Owner NANJING LONGYUAN MICROELECTRONICS TECH CO LTD
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