Text Recognition Method, Device, Equipment and Medium

Abstract

The present application provides a text recognition method, apparatus, device and medium, which relate to the field of artificial intelligence technology and are used to improve the efficiency of text recognition. In this text recognition method, target visual features in the text region to be recognized in the image to be recognized are extracted through a target text recognition model, and the target visual features are decoded to obtain a text recognition result, without performing deep encoding on the target visual features, so as to improve the efficiency of text recognition. Moreover, since the target text recognition model is trained by means of an attention encoder-decoder model, the target text recognition model can learn visual features more valuable for text recognition and improve the accuracy of text recognition.

Images