Arbitrary product photographing identification method based on mobile device

Abstract

The invention discloses an arbitrary product photographing identification method based on a mobile device, and the method comprises the following steps: S1, user login: a user searches a Sorftime Show applet in WeChat software, the Sorftime Show applet determines whether the user is a registered user through a user login system, if the user is the registered user, the user can directly log in, S2, product photographing is carried out, the logged-in user manually shoots picture information needing product identification through a shooting function of the Sorftime Show applet, a data analysis unit of the Sorftime Show applet carries out data analysis on the shot picture information, and shooting identification can be directly carried out in the Sorftime Show applet of a mobile phone terminal, therefore, a seller can inquire the market on the mobile phone anytime and anywhere; a seller does not need to entangle the keywords and does not need to cause analysis result deviation due to keyword search errors, and the market report can be quickly inquired by directly photographing.

Description

technical field [0001] The invention discloses a method for photographing and identifying any product based on a mobile device, and belongs to the technical field of photographing and identifying. Background technique [0002] Image recognition refers to the technology of using computers to process, analyze and understand images to identify targets and objects in various patterns. It is a practical application of deep learning algorithms. At this stage, image recognition technology is generally divided into face recognition And commodity recognition, face recognition is mainly used in security inspection, identity verification and mobile payment; commodity recognition is mainly used in the process of commodity circulation, especially in unmanned retail areas such as unmanned shelves and smart retail cabinets. [0003] Existing photographic recognition technologies are widely used, including photographic recognition of commodities. However, most of the existing photographic r...

AI Technical Summary

Problems solved by technology

[0003] Existing photographic recognition technologies are widely used, including photographic recognition of commodities. However, most of the existing photographic recognition of commodities requires computer operation, which is inconvenient to use. Although a few e-commerce platforms can photograph and recognize commodities, retrieval The product information only has price information, and it is impossible to understand the market of the product in an all-round way.