Relevant feedback retrieval method based on clustering in network image search
A network image and related feedback technology, applied in the field of network image search, can solve the problems of taking a long time and patience, time-consuming and laborious, boring, etc., and achieve the effect of reducing the workload of labeling, avoiding clicking on images, and avoiding semantic ambiguity.
Inactive Publication Date: 2010-07-21
TSINGHUA UNIV
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, there are certain shortcomings in this method of relying on annotations, that is, the retrieval results are directly related to the number of annotated images, so many images must be annotated to obtain good retrieval results; however, looking through the images one by one and annotating them, This process takes a long time and patience, it is a boring, time-consuming and laborious work
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0017] The related feedback retrieval method based on clustering in the network image search proposed by the invention is applied to the network image search. The flow process of the inventive method is as figure 1 shown, including the following steps:
[0018] 1) The user first inputs one or more keywords, and uses a keyword-based retrieval tool to obtain and return the first round of image retrieval results and display them to the user;
[0019] 2) Cluster the retrieved first n images according to the underlying features, and display the clustered image package to the user (the value range of n is generally determined by the user's needs, if n is too small, the user will not get satisfactory results , n too large will affect the calculation speed, generally take 500-1000); users mark these image packages;
[0020] 3) Sorting the images of the first round of retrieval results according to the annotations, and displaying the sorted new retrieval results to the user.
[0021...
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
Login to View More Abstract
The invention relates to a related feedback retrieval method based on clustering in a network image search, which belongs to the technical field of computer multimedia. The method includes: a user firstly inputs one or a plurality of key words and uses a retrieval tool based on the key words to obtain and return the retrieval result of the images in the first round; the retrieved first n images are clustered according to bottom characteristics and clustered image packages are shown to the user; the user marks the image packages; and the images of the retrieval result in the first round are scheduled according to the marks and the new retrieval results after being scheduled are shown to the user. The method optimizes the picture retrieval function of a present network image search engine, improves the retrieval accuracy and simultaneously can be widely applied to the retrieval of other image databases beyond the network.
Description
technical field [0001] The invention belongs to the field of computer multimedia technology, in particular to network image search technology. Background technique [0002] In recent years, with the development of image acquisition equipment and storage equipment, the number of digital images on the network is also increasing rapidly. In order to find the desired content in the vast image resources on the Internet, effective search tools and mechanisms are needed. However, existing search engines, such as Google, Baidu, etc., only support the image retrieval function based on keywords. This kind of text-based retrieval has many disadvantages, for example, the same semantics can be expressed in many different ways, and the meaning expressed by the same word will vary according to the context. In this case, when a keyword is input, the retrieval results obtained are usually huge in number and mixed in content, and the user has to rummage through them patiently to lock in the...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06F17/30
Inventor 戴琼海尔桂花路瑶
Owner TSINGHUA UNIV