Natural scene text identification method based on convolution attention network

Abstract

The invention discloses a natural scene text identification method based on a convolution attention network; the method comprises the following steps: using a two-dimensional convolution CNN as an encoder, extracting High-level semantic features of an input image, and outputting a corresponding feature graph to a decoder; using a one-dimensional convolution CNN as the decoder, combining an attention mechanism to integrate the High-level semantic feature formed by the encoder with a character level language model, thus forming a decode character sequence corresponding to the input image. For asequence with the length of n, the method uses the CNN modeling character sequence with a convolution kernel as s, and only O (n / s) times of operation is needed to obtain the long term dependence expression, thus greatly reducing the algorithm complexity; in addition, because of convolution operation characteristics, the CNN can be better paralleled when compared with a RNN, thus performing advantages of GPU resources; more importantly, a deep model can be obtained via a convolution layer stacking mode, thus improving abstractness expression of a higher level, and improving the model accuracy.

Description

technical field [0001] The invention relates to the field of text recognition in natural scene images, in particular to a method for recognizing text in natural scenes based on a convolutional attention network. Background technique [0002] With the increasing popularity of terminal devices such as mobile phones and tablets, it is becoming more and more important to recognize and understand images taken in natural scenes containing text. Due to factors such as image quality, complex background, and noise interference, text recognition in natural scenes faces great challenges. A complete end-to-end natural scene text recognition generally includes two stages: the text detection stage and the text recognition stage. The text detection stage locates the location of the text from the whole image, and the text recognition stage converts the image blocks containing only text into text strings. [0003] At present, due to the good language modeling ability of Recurrent Neural Ne...

AI Technical Summary

Problems solved by technology

For a sequence of length n, using RNN to model character sequences requires O(n) operations to obtain long-term dependent expressions, that is, the algorithm complexity is high

Images