Image retrieval method used in e-commerce platform

An e-commerce platform and image retrieval technology, applied in the field of similar product image retrieval, can solve the problem of difficulty in expressing consumers' retrieval wishes and other problems

Inactive Publication Date: 2011-04-20
INST OF AUTOMATION CHINESE ACAD OF SCI
View PDF1 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

There is no method of organizing products based on the information contained in the product pictures without relying on product labels; and at present, on e-commerce websites, consumers' retrieval is passive, and it is difficult to express consumers' retrieval wishes

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 retrieval method used in e-commerce platform
  • Image retrieval method used in e-commerce platform
  • Image retrieval method used in e-commerce platform

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0018] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be described in further detail below in conjunction with specific embodiments and with reference to the accompanying drawings.

[0019] The invention is a method for retrieving images of similar commodities on an e-commerce platform. The method can realize retrieval of commodity images without relying on the text labels of commodities. Moreover, the retrieval method can well meet the flexibility of consumers' attention requirements on commodities, and uses the scoring of different feature retrieval results, and then weights and adds the scores to obtain the final retrieval result.

[0020] The software and hardware environment that we realize to this inventive method: common PC, Intel Core2 CPU2.33GHz, internal memory 2.0G, integrated graphics card, Windows operating system, the compiling environment of VC++6.0.

[0021] Such as figure 1 Show 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 retrieval method used in an e-commerce platform. The method comprises the following steps: 1) the appearance characteristics of all the product images in a product image library are extracted and described with statistical histogram vectors to ensure that the extracted product appearance characteristics has robustness to the scale, rotation and translation transformation of each image; then the nearest neighbor search method is adopted to calculate the Euclidean distances of all the product appearance characteristics in the image library of the same type of products and the Euclidean distance of the appearance characteristics of a product to be searched and obtain a product image rank according to the different product appearance characteristics; 2) scoring is performed according to the rank and the similarity; and 3) a consumer combines the different characteristics of the same type of products according to different attentions to the product image appearance aspects, the score of each characteristic is multiplied by the corresponding attention weight value, the scores are added together, and the rank of the product images which is most similar to the product searched by the consumer is obtained according to the aggregate score.

Description

technical field [0001] The invention belongs to the technical field of pattern recognition and information processing, and relates to the processing of commodity images on an e-commerce platform, in particular to an implementation scheme for retrieving similar commodity images based on content information of commodity images. Background technique [0002] On the current e-commerce platform, most consumers search for the products they need through different brands, price rankings, product categories and sales volume. For consumers, these searches are not highly autonomous, and consumers accept them passively, and seldom take into account the aspect of product appearance that has a relatively large impact on human eyes. [0003] The display of commodities is mostly realized in the form of commodity images. The display form is product pictures from different angles, allowing consumers to have a more comprehensive understanding of the product. In addition, in the organization ...

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
Inventor 张荣国王春恒蔡新元邵允学肖柏华
Owner INST OF AUTOMATION CHINESE ACAD OF SCI
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