Restoring camera-captured distorted document images

Abstract

This article discusses restoration of cameracaptured distorted document images. Without the assistance of 3D data or model, our algorithm estimates and rectifies document warping just from 2D image based on line segmentation. Warping shape of each text line is acquired by estimating baselines' shape and characters' slant angles after line segmentation. In order to get fluent recovery result, thinplate splines are exploited whose key points are determined through the result of warping estimation. Such process can effectively depict document warping and successfully restore warped document images to be flat. Comparison of OCR recognition rate between original camera-captured images and restored images shows the effectiveness of the algorithm proposed. We also demonstrate evaluation on DFKI dewarping contest dataset with some related algorithms. Besides desirable restoration result, processing speed of the whole procedure is satisfactory as well. In conclusion, it is applicable to be performed in OCR application to achieve better understanding of camera-captured document images.

Enhancement of Old Document Image after Restoration with Morphologycal Approach

“…The case that often appears while document digitization process is that the character in the document becomes curved. Changsong Liu et al proposed thin plates splines algorithm to estimateds warping shapes of each text line and rectifies it [2]. There are 48 images which used in this study are devided into 4 groups based on noise type.…”

“…Identify the character which is contained in old documents image will determine the apropriate methods or techinque for the image. This identification result will avoid any assumption about the structure or content of the documents through texture feature calculation [2]. Documents that are stored too long with poor storage methods cause documents to be damaged.…”

Automatic rectification of warped Bangla document images

“…The ‘soft’ methods generally consist of two sub‐steps, namely implicit or explicit warp estimation and distortion correction. As per the warp estimation is concerned, the existing related methods can be classified into two categories: two‐dimensional (2D) and 3D [1]. In the case of 3D methods, the shape of a page is estimated and transformed into a 3D shape using some geometric models.…”

“…This ‘ matra ’ is used to the text line alignment in the document image. According to Liu et al [1] polynomial fitting is not very suitable for drawing baseline from warped image (for English script). It is difficult to estimate the degree of the polynomial needed for a particular text line.…”

Restoration Method of Distorted Digital Document Image Based on Text Line Detection

“…In order to get fluent recovery result, thin-plate splines are exploited whose key points are determined through the result of warping estimation [2].…”