Handwritten text recognition method and computer storage medium

Abstract

The embodiment of the invention provides a handwritten text recognition method and a computer storage medium. The method comprises the steps of encoding image contour features of a to-be-identified handwritten text image through an encoder based on a feature pyramid network in a first handwritten text identification model, so as to obtain a plurality of image contour feature data of different scales of the handwritten text image, performing multi-scale feature fusion on the plurality of image contour feature data of different scales to obtain image contour feature fusion data of the handwritten text image; performing residual decoding on the image contour feature fusion data of the handwritten text image through a residual decoder in the first handwritten text recognition model to obtain character posterior probability distribution data of handwritten characters in the handwritten text image; and recognizing a handwritten character recognition result of the handwritten text image based on the character posterior probability distribution data of the handwritten characters in the handwritten text image through a connection time sequence classification layer in the first handwritten text recognition model.

Description

technical field [0001] The embodiments of the present invention relate to the field of intelligent text recognition, in particular to a handwritten text recognition method and a computer storage medium. Background technique [0002] Since handwritten text images in real scenes are very complex, the images often contain distorted or overlapping characters, characters of different fonts, sizes and colors, and complex background noise. Therefore, textual information in images for text recognition tasks is essential for visual semantic understanding tasks. However, handwritten text recognition is different from traditional OCR (Optical Character Recognition, optical character recognition). The main reason is that everyone has different writing habits, which are reflected in font, size, density and even direction. [0003] The text recognition methods in the prior art have a good recognition effect on written and printed text, but poor recognition effect on handwritten text, and...

AI Technical Summary

Problems solved by technology

[0003] The text recognition method in the prior art has a good recognition effect on written and printed text, but the recognition effect on handwritten text is poor, and cannot adapt to the style changes of handwritten fonts

Specifically, handwritten text lines also have fonts with variable scales and font intervals with different densities, resulting in serious missing characters in recognition

In addition, text recognition of low-quality handwritten text images such as blurred images of handwritten fonts, distorted images of handwritten fonts, and images of handwritten fonts with variable sizes is less robust

Images