General Document Image Correction Method Based on Text Line in Natural Scene

Abstract

This paper presents a general document image correction method based on the text line. The proposed method roughly screens the text area and implements rotation correction based on the TextSnake text detection model. Then by the relative positions of characters, the principle of text direction consistency and the two-way matching strategy, the precise positioning is realized. At last, the information of text ridges is obtained to acquire the nonlinear mapping relationship of the whole graph, Therefore achieving correction reconstruction of the general document image. The experiment results show that the correction method can overall solve image quality problems such as tilt distortion and improve the recognition rate of tilt distortion image.