Amir Reza Ghods - Electrical and Computer Engineering Department, Semnan University, Semnan, Iran
Saeed Mozaffari
Farhad Ahmadpanahi

This paper presents a novel approach for document de-warping using Microsoft Kinect camera sensor. The proposed method makes use of the 3D model of the warpeddocument using Kinect sensor. Due to the low resolution of Kinect’s RGB camera, an external high resolution camera isused for capturing a higher quality image. The point cloudcaptured by Kinect depth sensor is down sampled and then the voxilized grid approach is applied. Then a triangulation mesh isgenerated using greedy fast triangulation method. In the next step, a conformal 3D to 2D mapping is applied to the curvedmesh. This creates a flat plane of the 3D mesh. Eventually, the original image is converted to the flatted version by a 2D to 2Dmapping method. Text independency of this methoddistinguishes it from the other methods which use the document text lines to estimate the curvature of the plane. By using this method, documents with different distortions and with any kind of content such as pictures, graphs and tables can be dewarped.

De-warping, Kinect sensor, RGB-D sensor, De-skewing, 3D document image processing