End-to-end scene character detection and recognition method and system

Abstract

The invention provides an end-to-end tendency scene character detection and recognition method and an end-to-end tendency scene character detection and recognition system. The method comprises the steps: collecting pictures marked with object types, constructing a training data set and a test data set, and carrying out the preprocessing of the data sets for training a feature extraction network; collecting pictures marked with character positions, constructing a training data set and a test data set, and preprocessing the data sets to train a network of a character detection part; pictures marked with character positions and character contents at the same time are collected, a training data set and a test data set are constructed, and corresponding picture preprocessing is carried out to train a neural network of a character recognition part; inputting the picture into a convolutional neural network; extracting a shared convolution feature map through a feature extraction network; andmapping predicted character position coordinates to the shared convolution feature map by the character detection part maps by using the shared convolution feature map, cutting off a feature map blockcorresponding to the character part in the image and converting the feature map block into a feature sequence; finally decoding the feature sequence into a readable character sequence. Since the convolution characteristic spectrum is only calculated once, the intermediate redundancy process is avoided. The speed of the whole scene character detection and recognition system is improved.

Description

technical field [0001] The disclosure belongs to the technical field of text detection and recognition, and in particular relates to an end-to-end scene text detection and recognition method and system. Background technique [0002] The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute prior art. [0003] As the greatest invention of mankind, text is one of the main ways for people to transmit and interact with information. Pictures are one of the main carriers of text, so reading text from pictures has important practical value. [0004] As far as the inventor understands, the traditional processing method generally detects the position of the text on the original input image by a text detection algorithm earlier, and circles the text with a text box; then utilize methods such as Opencv to cut out the area where the text is located from the picture; Finally, a text recognition algorithm is ...

AI Technical Summary

Problems solved by technology

This algorithm separates the position detection of the text from the content recognition of the text, and there is a time difference and a difference in order. At the same time, since the text detection algorithm and the text recognition algorithm need to use the convolutional neural network to extract the feature map, a lot of time is wasted. At the same time, text detection and text recognition are regarded as two unrelated tasks, so that detection and recognition cannot promote each other, which will increase the complexity of the system and is not conducive to improving the speed and accuracy of the entire system

Images