Interactive type image search system and method

An image search and interactive technology, applied in the field of image search system, can solve the problems of fully automatic segmentation difficulty, difficult search, high calculation amount, etc., and achieve the effect of reducing operation complexity, increasing application range, and improving search accuracy

Active Publication Date: 2008-07-09
上海博康智能信息技术有限公司
View PDF0 Cites 83 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, fully automatic segmentation of arbitrary images is a difficult problem
The current existing system adopts the method of fully automatic segmentation, and it is still unable to ideally extract the complete area of ​​an object.
The current segmentation method often divides an object into many

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
  • Interactive type image search system and method
  • Interactive type image search system and method
  • Interactive type image search system and method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0040] This embodiment is an interactive image search system, the block diagram of which is shown in Figure 1, including two parts: client and server. The client can be a computer terminal or a mobile phone. Includes the following modules:

[0041] The image acquisition module can be realized in many ways, such as taking a picture through a camera, or finding a picture in a picture library in a computer, and so on.

[0042] The user selects a module to select the region of interest of the picture and the category of the object to be recognized.

[0043] Image segmentation and feature extraction module, the function is to automatically segment the foreground area with the foreground extraction method according to the area and category selected by the user, and then extract image features in the foreground area.

[0044] The communication module, including the Internet or wireless network, is used to transfer information between the client and the server.

[0045] The functio...

Embodiment 2

[0049] This embodiment is another interactive image search system, the block diagram of which is shown in Figure 2, including two parts: client and server. The client can be a computer terminal or a mobile phone. Includes the following modules:

[0050] The image acquisition module can be realized in many ways, such as taking a picture through a camera, or finding a picture in a picture library in a computer, and so on.

[0051] The user selects a module to select the region of interest of the picture and the category of the object to be recognized.

[0052] Image segmentation and feature extraction module, the function is to automatically segment the foreground area with the foreground extraction method according to the area and category selected by the user, and then extract image features in the foreground area.

[0053] The communication module, including the Internet or wireless network, is used to transfer information between the client and the server.

[0054] The fu...

Embodiment 3

[0058] This embodiment is an e-commerce information retrieval system using the interactive image search system of the present invention, the block diagram is the same as that shown in system block diagram 1, including two parts, the client and the server. The client can be a computer terminal or a mobile phone. Includes the following modules:

[0059]The image acquisition module can be realized in many ways, such as taking a picture of a product with a camera, or finding a picture of a product in a picture library in a computer, and so on.

[0060] The user selects a module to select the region of interest of the image and the product category to be recognized.

[0061] Image segmentation and feature extraction module, the function is to automatically segment the foreground area with the foreground extraction method according to the area and category selected by the user, and then extract image features in the foreground area.

[0062] The communication module, including the...

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 an image search system and a method which is an interactive image search system and method. The method includes the following steps: the user selects objective photos, area interested and the object category to be identified; automatically partitioning the foreground area by a foreground extraction method according to the area and category selected by the user and extract the image features in the foreground area; searching the matching images in the image database of the specific category according to the image features; acquiring the related objective information according to the matching images and return the information of the matching image to the user. For any image, the invention can effectively extract the objective information from the image, thus realizing an elaborated search of the object in an image. Meanwhile the invention combines the category information of target objectives into the image search, thus effectively improving the search precision and reducing the operation complexity. The invention realizes an image-search-based e-commerce system.

Description

technical field [0001] The invention relates to an image search system and method, in particular to an interactive image search system and method. Background technique [0002] With the development of the Internet, search engines have become an important tool for information acquisition and commodity marketing. The traditional way of searching for information is to use words to search. Examples in this regard include Google, Baidu and so on. However, it is difficult to describe complex image information only by text search, so the next generation of information search methods must require image search. [0003] The basic principle of the image search system is to construct a database for search by analyzing the visual characteristics of the image by computer, so as to realize the search. Traditional image search methods use the method of analyzing the whole picture, which is suitable for rough search, such as distinguishing pictures of blue sky, beach, and woods. But doin...

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): G06F17/30G06T7/00G06K9/46G06K9/62
Inventor 虞正华
Owner 上海博康智能信息技术有限公司
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