Camera Captured Document De-Warping and De-Skewing

Abstract

De-warping is the elementary step in the analysis of document images which are camera based. Processing of warped image is a challenging task. Therefore, to make the document images OCR understandable de-warping has become a major task. In this paper, we have presented an effective pre-processing, de-warping and de-skewing techniques for camera captured document image processing. In pre-processing, we have divided input color document image into R, G and B-band, further convert R, G, B-band to C, M and Y-color space respectively, convert the average CMY grey scale image to binary by determining threshold value automatically. In de-warping and de-skewing, we have presented an effective techniques to remove geometrical and perspective distortion in camera captured document by combination of centroid and mid-point of bounding box height, bounding box is plotted on text blocks using connected component analysis technique. The introduced work is robust in correcting geometric distortion and skew correction for standard printed data set and also for Kannada handwritten documents.

Adaptive dewarping of severely warped camera-captured document images based on document map generation

“…Around 101 samples of assessments of very few distortions and skew are considered for experimentation. In work by [ 35 ], dewarping and deskewing are performed based on various color band details of CMY using a threshold. Removal of geometrical and perspective distortion using centroid and mid-point of bounding box height and connected components is accomplished.…”