Image search method and image search device

A picture search and picture technology, applied in the field of network search, can solve problems such as unusable and ineffective use of server resources, and achieve the effect of improving the utilization rate

Inactive Publication Date: 2013-06-05
ALIBABA GRP HLDG LTD
View PDF11 Cites 52 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0016] In practical applications, the above-mentioned image search technology based on visual features is mainly based on re-establishing a search engine based on visual features, instead of using the text search engine that is generally available in existing servers with search functions, so that it cannot be effectively used. server resources

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 search method and image search device
  • Image search method and image search device
  • Image search method and image search device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] Embodiment 1 of the present application provides a picture search method, which can be applied to a server with information search function in the Internet, so as to use the text search engine of the server to search pictures, thereby improving the utilization rate of server resources.

[0047] In order to achieve the above-mentioned purpose of using the text search engine of the server to search for pictures, in the picture search method provided in the first embodiment, it is necessary to establish tags for each picture in the picture search library in advance, as the basis for the server to search for pictures, as follows: Two preferred implementations of establishing tags for each picture in the picture search library are described.

Embodiment approach 1

[0049] In the first preferred embodiment, labels are mainly generated for each picture in the picture search library, and the corresponding relationship between labels and pictures is mainly stored.

[0050] image 3 It shows a schematic flow chart of establishing labels for each picture in the picture search library, as shown in image 3 As shown, the process mainly includes the following steps:

[0051] Step 301, select a picture from the picture search library, and obtain the description information corresponding to the picture.

[0052] In the step 301, the process of acquiring the description information of the picture includes: determining the entity corresponding to the picture, and acquiring the description information of the entity as the description information corresponding to the picture. Specifically, the description information corresponding to the picture is mainly used to characterize the attributes of the entity corresponding to the picture, and the descriptio...

Embodiment approach 2

[0062] In the second preferred embodiment, in addition to generating labels for each picture in the picture search database, the visual features of the pictures are further extracted, and when the correspondence between labels and pictures is saved, the correspondence between labels and visual features is also saved, that is The label generated for the picture, the picture corresponding to the label, and the corresponding relationship of the picture features extracted from the picture are stored.

[0063] Figure 4 It shows a schematic flow chart of establishing labels for each picture in the picture search library, as shown in Figure 4 As shown, the process mainly includes the following steps:

[0064] Step 401, select a picture from the picture search library, and obtain the description information corresponding to the picture.

[0065] The specific implementation process of this step 401 is basically the same as the specific implementation process of the above-mentioned ...

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 search method and an image search device. The image search method comprises the steps of in allusion to images in an image search base, generating a label corresponding to each image according to corresponding description information of each image, saving the generated label and congruent relationships of the images, when image search is carried out, according to a received image search request, obtaining description information of a to-be-searched image which is included in the request, a label corresponding to the to-be-searched image is generated according to the description information, wherein the mode of generating the label corresponding to the to-be-searched image and the mode of generating the label corresponding to each image in the image search base are the same, further determining an image which corresponds to the label of the to-be-searched image according to the congruent relationships between the saved labels and the images, and sending the determined image to a sending end of the image search request. The image search technology based on the labels is capable of using an existing text search engine, and therefore use ratio of server resources is improved.

Description

technical field [0001] The present application relates to the technical field of network search, in particular to a picture search method and a picture search device. Background technique [0002] With the application and continuous development of image search technology, the search technology based on visual features is currently the mainstream search technology. The realization of this search technology requires the establishment of an image search library based on visual features in advance. Specifically, figure 1 It shows a schematic flow chart of establishing an image search library based on visual features, and the establishment process mainly includes the following steps: [0003] Step 101, establishing a feature extraction system, in which a visual feature template to be extracted from a picture is defined. [0004] Step 102, using the established feature extraction system to extract visual features from each picture in the picture search library, that is, to repres...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06F17/30
CPCG06F17/30268G06F17/30244G06F17/30247G06F16/50G06F16/583G06F16/5866G06F16/53
Inventor 金华兴
Owner ALIBABA GRP HLDG 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