Geometric Distortion Correction Technique of Text Images

Abstract

The rapid distribution of digital cameras has caused several new problems related to text recognition. Based on experimental studies, it was revealed that existing OCR systems cannot cope with a complex perspective and geometric distortions that arise during photographing text documents. Therefore, it is necessary to apply text documents pre-processing, so the text lines were straight and horizontal. This article briefly considers the methods document pre-processing, and found that it depends on the type of distortion and is not universal. We proposed information technology and a new method involving the mathematical raising of straightened text lines on the image and heterogeneous distortion correction based on a page surface transformation model. This technology is more reliable than others as it is universal and corrects any type of geometric distortion, including a combination of several types of distortion.KeywordsInformation technologyRecognitionOptical recognition systemText document imageImage distortion