Image character recognition method and system based on deep learning and medium

Abstract

The invention provides an image character recognition method and system based on deep learning and a medium. The method comprises the steps that the source category of an image is judged; extracting an image target area through a convolutional neural network and classifying the target area; carrying out orientation correction on the image of the target area, rotating the image to a forward orientation, and calculating an inclination angle of the image through line segment detection and a frequency domain signal analysis method; calculating a feature map of the image by using a target detectionalgorithm and a deep convolutional network, and carrying out target segmentation on the text line to carry out character recognition; according to a CRNN algorithm, combining the deep convolutional network with a bidirectional cyclic network, and carrying out end-to-end network training; and obtaining the position of the character in the picture and the model recognition content through training,and extracting character information. By adopting the computer vision and character recognition technology, the recognition problem of bill cards and table document data in the intelligent auditing process in the financial field is solved.

Description

technical field [0001] The present invention relates to the technical field of deep learning and image recognition, in particular to a deep learning-based image character recognition method, system and medium. Background technique [0002] With the popularization of smart phones and mobile devices, pictures are used in more and more scenarios as the carrier of information dissemination. Manually extracting key information of certificates and bills in the original business process is often inefficient because of the lengthy fields, so there is also an increasing demand for image text recognition. The extraction of key information in bills and forms through OCR technology has become a means to improve the efficiency of information entry. [0003] The traditional OCR processing flow includes text detection, single-character segmentation, single-character recognition, post-processing and other processes. The more representative one is the PhotoOCR algorithm proposed by Google, ...

AI Technical Summary

Problems solved by technology

[0003] The traditional OCR processing flow includes text detection, single-character segmentation, single-character recognition, post-processing and other processes. The more representative one is the PhotoOCR algorithm proposed by Google, which includes text area detection, text line merging, over-segmentation, and Beam Search-based Segmentation area combination, single-character classification based on HOG features and full-link neural network, etc., but this method needs to split the OCR system into too many links, and needs to introduce too much manual intervention in each link, and needs to be set according to the scene Method integration makes it difficult to achieve end-to-end training and deployment, and the cost of use is too high

[0004] And in the identification service production process, the fragmentation between the original systems leads to high cost of data collection process for a long time, and the poor efficiency of upstream and downstream information transmission leads to slow technology application

Images