Searching shopping method based on pictures

Abstract

The invention discloses a searching shopping method based on pictures. The method includes the steps that first, a user uploads a goods picture needing to be searched for to a server from a terminal, the uploaded goods picture is subjected to feature classification on the server side, a picture feature value is extracted, and searching is conducted in a goods picture index file through the obtained picture feature value; then the searched goods picture and goods information are recommended to the user by the server according to the research results of similar goods. By combining the picture feature value of the goods picture, the needed goods can be searched for more accurately in the searching process, meanwhile, further manual retrieval or searching based on visual features is avoided, and the searching shopping convenience and accuracy are improved under the condition that the appearance of the needed goods is known. Moreover, an existing hand-held terminal generally has a photographing function, when the user sees the goods which he or she pays close attention to in a market or other places, the user can take a picture and send the picture to the server, and accordingly the goods picture and the goods information can be searched for accurately and conveniently for shopping.

Description

technical field [0001] The invention relates to the technical field of electronic commerce, in particular to an image-based search and shopping method. Background technique [0002] In e-commerce, the traditional search and shopping method is based on commodity classification retrieval or keyword search. However, due to the wide variety of commodities, the same commodity also has many different models, the accuracy of retrieval or search is not high, and it is necessary to check and retrieve one by one Or searched products, so users still have a certain amount of cumbersomeness in searching and shopping for products. [0003] With the rapid development of e-commerce, the traditional text-based search and shopping methods can no longer meet the needs of users. The attraction of products to users is mostly based on the attraction of visual features. Users hope that they can get product information and purchase through product pictures. Information, you can immediately search ...

AI Technical Summary

Problems solved by technology

[0002] In e-commerce, the traditional search and shopping method is based on commodity classification retrieval or keyword search. However, due to the wide variety of commodities, the same commodity also has many different models, the accuracy of retrieval or search is not high, and it is necessary to check and retrieve one by one or searched products, so users still have a certain amount of cumbersomeness in searching and shopping for products

[0003] With the rapid development of e-commerce, the traditional text-based search and shopping methods can no longer meet the needs of users. The attraction of products to users is mostly based on the attraction of visual features. Users hope that they can get product information and purchase through product pictures. Information, you can instantly search for product information and purchase information through the terminal when you see your favorite product for shopping

Images