Unlock instant, AI-driven research and patent intelligence for your innovation.

Sorting method of unlabelled pictures for network search

A technology of network search and sorting methods, applied in special data processing applications, instruments, electrical digital data processing, etc.

Inactive Publication Date: 2012-03-07
ZHEJIANG UNIV
View PDF2 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, CBIR technology is only suitable for small environments such as the search of databases in the scientific research field, but not for actual large environments such as Internet searches.

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
  • Sorting method of unlabelled pictures for network search
  • Sorting method of unlabelled pictures for network search
  • Sorting method of unlabelled pictures for network search

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053] In order to describe the present invention more specifically, the technical solution of the sorting method of the present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0054] Such as figure 1 As shown, a method for sorting unlabeled images for web search, including the following steps:

[0055] (1) Collect several reference pictures according to the query information.

[0056] Submit the query keyword Q given by the user to a third-party image search engine (such as Google Image Search Engine), and collect the top 100 images from the search results as reference images, denoted as G 1 ~G 100 .

[0057] (2) Calculate the correlation between each reference picture and the query information.

[0058] 1. Submit the query keyword Q to a third-party web search engine (such as Google web search engine), and collect the top 200 web pages from the search results as reference web pages, denoted as D 1 ~D ...

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 a sorting method of unlabelled pictures for network search, comprising the following steps of: (1) collecting several reference pictures according to query information; (2) calculating relevancy of each reference picture to the query information; (3) calculating similarity among the reference pictures; (4) amending the relevancy according to the similarity; and (5) sortingthe unlabelled pictures according to the amended relevancy. In the method, artificial intelligence related technologies are used, web search and image search results are mined while querying the information, and the relevancy of the unlabelled pictures to the query information is estimated according to the similarity among the reference pictures so as to sort the unlabelled pictures accurately, so that users can search and get the unlabelled pictures, and the searching result is better.

Description

technical field [0001] The invention belongs to the technical field of network search and sorting, and in particular relates to a method for sorting unlabeled pictures used in network search. Background technique [0002] As early as the 1970s, researchers from various countries began to study how to effectively manage image data. The technology used at that time was mainly text-based image retrieval technology (TBIR), which refers to inputting a series of images for images by manually inputting text. keyword, and then establish a link between the storage path of the image and the image keyword, and the image retrieval actually becomes a text retrieval. This method is simple and easy, and can be realized with a traditional relational database, but there are also some shortcomings. , if the workload of manually inputting keywords is too large, it is impractical to identify keywords for massive image data, and manual identification will inevitably bring personal subjectivity a...

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): G06F17/30
Inventor 徐颂华江浩刘智满
Owner ZHEJIANG UNIV