Recognition method for English words and digits in natural scene image

Abstract

The invention provides a recognition method for English words and digits in a natural scene image. According to the method, recognition of the English words and the digits in a natural scene is divided into a feature extraction step, a feature focusing step and a feature recognition step, wherein a convolutional neural network is utilized to perform feature extraction on an input image, an attention mechanism is utilized to focus on useful information in a feature sequence, a long and short-time memory network is utilized to recognize feature vectors, therefore, a deep neural network and the attention mechanisms are combined, and a final recognition result can be obtained directly when the image is input into the deep neural network. Through the method, it is not needed to perform winding sliding operation on the input image or recognize characters in a window; and meanwhile, an output string is the final recognition result, so that it is not needed to integrate recognized strings through a merging algorithm.

Description

technical field [0001] The invention belongs to the technical field of character recognition, and relates to a method for recognizing English characters and numbers in natural scene images by using a deep neural network and an attention mechanism. Background technique [0002] Text in natural scenes often carries very important information, which can be used to describe the content of the image. Automatically obtaining text information in images can help people understand images more effectively and perform storage, compression, retrieval and other processing on images. Compared with the natural scene text detection method, the natural scene text recognition method is to recognize the detected text area. As a universal language in the world, English and numbers appear widely in scenes all over the world, and it is of great significance to recognize English words and numbers. However, unlike handwritten character recognition, the position, size, font, lighting, viewing angl...

AI Technical Summary

Problems solved by technology

However, this method has two limitations: 1. The accuracy of character recognition using the sliding window method and traditional classifiers is not high; 2. The character recognition and merging algorithms are trained separately, and the errors generated by them will be directly passed to the final classifier. In the recognition results, the text recognition accuracy is not high

Images