Model training method and device, text recognition method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a model training method and device, a text recognition method and device, electronic equipment and a storage medium, and is applied to the technical field of artificial intelligence. The model training method comprises the steps of acquiring multiple first sample images containing bent texts and text information of the bent texts in the first sample images;respectively inputting the first sample image into an image correction model and a text recognition model, and performing feature extraction on the first sample image through the image correction model to obtain a first image feature; performing feature extraction on the first sample image through the text recognition model to obtain a second image feature; determining a feature loss value according to the first image feature and the second image feature by using a preset feature loss function; and when the pre-trained text recognition model is trained through the first sample image and the text information in the first sample image, updating the text recognition model based on the feature loss value. The accuracy of text recognition can be improved.

Description

technical field [0001] The embodiments of the present application relate to the technical field of artificial intelligence, and in particular to a model training, a text recognition method and device, electronic equipment, and a storage medium. Background technique [0002] Natural scene text recognition is the process of recognizing character sequences from images containing text. For Chinese, a Chinese character is a character; for English, a letter is a character. In natural scene text recognition, due to the complex image background, low resolution, diverse fonts, random distribution, etc., and the text is composed of characters with a variable number, it is necessary to recognize sequences of variable length from the image. Therefore, the natural scene text Recognition is a challenging task. [0003] In related technologies, text information in an image can be recognized through CRNN (Convolutional Recurrent Neural Networks, Convolutional Recurrent Neural Networks). S...

AI Technical Summary

Problems solved by technology

[0004] In view of this, the embodiment of the present application provides a text recognition model training method, a text recognition method, a text recognition model training device, a text recognition device, electronic equipment, and a storage medium, so as to overcome problems in the prior art that contain curved text. When the image is used for text recognition, the defect of low accuracy

Images