Card-information acquisition method and system

Abstract

The scheme relates to a card-information acquisition system and method. The system includes an image acquisition module (201) for acquiring a card image; a database (205) for prestoring card information which at least includes the type of a card, image features and text composition information; an image analyzing and identifying module (203) for extracting image features from the acquired card image and comparing the image features with the image features in the card information prestored by the database (205) so as to determine the type of the card; a character identifying module (207) for extracting card information, which is corresponding to the type and includes the text composition information, from the database (205) according to the determined type of the card so as to locate character areas and segmented characters so that characters on the acquired card image are identified. The method includes a processing process of the system. In the card-information acquisition system and method, the card information of a card is used to establish the database and valid image features are used to identify the type of the card so that extraction performance and efficiency of information areas of the card are improved and automatic and rapid card-information input through use of a mobile terminal is facilitated for a user.

Description

technical field [0001] The present invention relates to the technical field of obtaining information on mobile terminals, and in particular to a method and system for obtaining card information by using image recognition on mobile terminals. Background technique [0002] With the rapid development of mobile terminals, there are more and more demands for payment on mobile terminals. Most payment-related businesses require users to enter their card information, such as credit card / bank card number and other information. Usually there are two ways to obtain this information: one is manual input, which is often prone to input errors, and complicated operations will cause trouble to users. The other is based on the traditional OCR (Optical Character Recognition) method, where the card is photographed by the camera, and then the area of ​​interest (such as the account information part) is located, and then the characters are segmented and recognized. [0003] It is a very inconv...

AI Technical Summary

Problems solved by technology

Wherein, the camera signal output end connected with the central processing unit of the mobile terminal does not utilize the prior information such as the card type that is very helpful for automatic entry, and its method is easy to be affected by various card backgrounds, textures, bumps, etc. of different types and styles. The influence of patterns, etc. (especially different types of cards) can easily lead to the failure of text content extraction and recognition, and it is necessary to scan the entire image to identify all text areas, and the operating efficiency is also low.

Images