Text detection and recognition method and system combined with text classification

Abstract

The invention discloses a text detection and recognition method and system combined with text classification. The method comprises the following steps: acquiring all target text line boxes in a target picture; cutting and extracting all the target text line frames to obtain a text graph; sending the text graph into a text direction classification model, and carrying out correction identification to correct the text graph in any direction to the same horizontal direction so as to obtain a text correction graph; sending the text correction graph to a character language classification model, and carrying out character language category recognition to obtain a character language category image; and sending the character language category image into a language text recognition model corresponding to the language category, and performing recognition to obtain a final text content. According to the invention, the problem that text detection in the prior art cannot detect texts with any shapes and complex scenes is solved; the conditions that the text is reversed and the direction is not positive cannot be detected; and the problems of high time cost and low efficiency caused by the fact that multi-language text regions need to be sent into a plurality of models for recognition are solved.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to a text detection and recognition method and system combined with text classification. Background technique [0002] In recent years, natural scene text detection and recognition technology has attracted extensive attention for its many applications such as scene understanding, instant translation, autonomous driving, and target geolocation. However, the effect of natural scene text detection and recognition is not ideal. The text detected by it has: inclined characters, artistic characters, deformed characters, fuzzy characters, similar characters, incomplete characters, light and shadow shading and multilingual mixing. [0003] The traditional text recognition system, using the image morphology operations in computer vision, including the basic operations of dilation and erosion, can realize text detection in simple scenes (texts with arbitrary shapes and complex scenes ...

AI Technical Summary

Problems solved by technology

[0005] In the embodiment of the present invention, a text detection and recognition method and system combined with text classification are provided to solve the problem that text detection in the prior art cannot detect texts with arbitrary shapes and complex scenes; and cannot detect text inversions and incorrect directions in the text In the case of multilingual texts, each text area needs to be sent to multiple models for recognition, resulting in a large time-consuming and low-efficiency problem

Images