OCR accuracy improvement on document images through a novel pre-processing approach

TL;DR

This paper introduces a novel, unsupervised pre-processing pipeline that enhances document images by correcting distortions and improving illumination, leading to significant improvements in OCR accuracy and text detection rates.

Contribution

The paper presents a new nonparametric, unsupervised method combining multiple image enhancement techniques specifically designed to improve OCR performance on distorted document images.

Findings

Significant increase in OCR accuracy on standard datasets.

Effective handling of lighting variations and distortions.

Improved text detection rates compared to baseline methods.

Abstract

Digital camera and mobile document image acquisition are new trends arising in the world of Optical Character Recognition and text detection. In some cases, such process integrates many distortions and produces poorly scanned text or text-photo images and natural images, leading to an unreliable OCR digitization. In this paper, we present a novel nonparametric and unsupervised method to compensate for undesirable document image distortions aiming to optimally improve OCR accuracy. Our approach relies on a very efficient stack of document image enhancing techniques to recover deformation of the entire document image. First, we propose a local brightness and contrast adjustment method to effectively handle lighting variations and the irregular distribution of image illumination. Second, we use an optimized greyscale conversion algorithm to transform our document image to greyscale level. Third, we sharpen the useful information in the resulting greyscale image using Un-sharp Masking method. Finally, an optimal global binarization approach is used to prepare the final document image to OCR recognition. The proposed approach can significantly improve text detection rate and optical character recognition accuracy. To demonstrate the efficiency of our approach, an exhaustive experimentation on a standard dataset is presented.