Image searching method and system, client side and server

An image search and client-side technology, applied in the field of image recognition and search, can solve the problems of affecting the query response time of the retrieval system, reducing the actual application of users, and large data volume, so as to facilitate the retrieval of various information, shorten the waiting time, and improve the The effect of response time

Active Publication Date: 2011-05-18
PEKING UNIV
View PDF3 Cites 27 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The serious problem with the above visual search method is: the amount of data sent by the client to the server is very large
Due to the limitation of the uplink bandwidth of the existing network, it takes a long time for the client to transmit large data to the server, which further leads to a long query response time on the server, which makes image retrieval inefficient
That is, the data transmission time from the client to the server seriou

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 searching method and system, client side and server
  • Image searching method and system, client side and server
  • Image searching method and system, client side and server

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0049] refer to figure 1 as shown, figure 1 It shows a flow chart of the steps of Embodiment 1 of the image search method in the present invention; wherein, the image search method in this embodiment includes:

[0050] Step 101: the client acquires a target picture to be searched and first associated information for the target picture. The target picture here is any picture. For example, the target picture can be a landmark picture, a picture of a book cover, a picture of a product's appearance, a global picture of a museum sign or a picture partially containing a barcode or an electronic label, or a landscape For photos and the like, the type and content of the target pictures are not limited in the present invention.

[0051] For example, if the target picture is selected from a landmark picture, the first associated information may be a building in the landmark picture, geographic location information corresponding to the landmark picture, geographic location information ...

no. 2 example

[0080] refer to figure 2 as shown, figure 2 It shows the flow chart of Embodiment 2 of the image search method in the present invention, and the specific steps include:

[0081] Step 201: Acquiring the target image to be searched and the first associated information on the client side;

[0082] Step 202: the client sends the first associated information to the server; the client extracts the global or local features of the target picture, and converts the features into visual words. It should be noted that the steps of the client extracting the features of the target image and sending its first associated information to the server are not sequenced. In addition, the visual word here can be a set of visual word data. In this field, a set of visual word data is usually briefly named with a visual word, so the name of the visual word is also used in this embodiment.

[0083] Specifically, the conversion steps of visual words include: first, use the existing feature detection...

no. 3 example

[0105] Landmarks refer to buildings or natural landscapes with unique geographical features in a city or place, such as skyscrapers, churches, temples, statues, lighthouses, bridges, etc. When the target picture is a landmark building. The associated information corresponding to the target picture may be geographic location information of landmarks and the like. The following uses a landmark image as an example for illustration. Involved in this example image 3 and Figure 4 For the process description, refer to image 3 and Figure 4 as shown, image 3 It shows a flow chart of dividing related information classes by spectral clustering method adopted in Embodiment 3 of the image search method of the present invention; Figure 4 It shows a flow chart of filtering out visual word dictionaries corresponding to associated information in Embodiment 3 of the image search method of the present invention.

[0106] The steps of the image search method in the third embodiment m...

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 provides image searching method and system and a client side and a server, wherein the image searching method comprises the steps: the client side obtains a target image to be searched and first relevance information aiming at the target image, sends the first relevance information to the server, and obtains a vision word of the target image; the server searches a vision word dictionary in a vision word dictionary library inside the server based on the first relevance information, and sends the vision word dictionary to the client side; the client side obtains a target vision word based on the vision word dictionary sent by the server and sends the target vision word to the server; and the client side receives the target vision word, searches more than one result image corresponding to the target vision word and relevant expansion information and sends the result image and the relevant expansion information to the client side. The image searching method shortens the searching waiting time of a client, improves the searching performance and the efficiency and can be suitable for various fields.

Description

technical field [0001] The present invention relates to the technical field of picture recognition and search, in particular to a picture search method, a picture search system, a client and a server. Background technique [0002] Currently, text-based video and picture retrieval technologies are very mature. However, because some pictures cannot be accurately described in words, many error messages or information not required by the user appear in the text search results. In recent years, a large number of research results on visual retrieval methods, that is, directly using images to search, have emerged at home and abroad, but the retrieval results of visual retrieval technology are still unsatisfactory, especially for the retrieval of massive image databases. Due to the large number of images in the database, the application Image retrieval technology based entirely on content cannot achieve satisfactory search accuracy and efficiency. [0003] Specifically, the steps ...

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 段凌宇纪荣嵘陈杰李冰黄铁军姚鸿勋高文
Owner PEKING 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