Prediction model construction method, device and system and bank card number identification method

Abstract

The invention discloses a prediction model construction method, device and system and a bank card number identification method, and belongs to the technical field of computers. The prediction model construction method comprises the following steps: acquiring a bank card sample image of a bank card and calculating the bank card sample image to obtain a candidate area; inputting the bank card sampleimage and the candidate region into a Fast-R-CNN model; and training the Fast-R-CNN model according to a preset classification label, the regression position corresponding to the classification label, a classification prediction result output by the Fast-R-CNN model and a regression position prediction result corresponding to the classification prediction result, and determining the trained Fast-R-CNN model as a prediction model. The method is different from most OCR methods, extra work such as character segmentation and image processing is not needed, the method is an end-to-end method, andrecognition errors caused by image segmentation and other processes can be avoided.

Description

technical field [0001] The invention belongs to the field of computer technology, and in particular relates to a prediction model construction method, device, system and bank card number recognition method. Background technique [0002] Online payment has become the first choice of most people, and many financial institution apps with payment functions require users to bind bank cards. Manually inputting the bank card number is not optimal in terms of user experience, and the optical character recognition (OCR) function of the bank card can provide users with a fast and convenient function of inputting the bank card number. Scan the bank card to automatically identify the card number, which greatly improves the user experience. However, traditional OCR methods usually require character segmentation and image processing in advance, and the obtained bank card number is limited by the quadrilateral and relative position of the bank card organization mark, and is easily affecte...

AI Technical Summary

Problems solved by technology

However, the traditional OCR method usually requires character segmentation and image processing in advance, and the obtained bank card number is limited by the quadrilateral and relative position of the bank card organization mark, and is easily affected by image segmentation and other processes, resulting in recognition errors.

Images