Captured open book image de-warping and shading correction using 3D depth information

Chyuan-Tyng Wu, Purdue University

Abstract

Various three dimensional (3D) measuring or capturing devices are introduced to the society recently, and there are abundant possibilities that we can take advantage of this new technology. In this research, we worked on one useful application: to correct the distortion due to the curved shape of the pages of an open book in captured images using of depth information. This work is relevant to camera-based capture devices that can use a projector to cast structured light patterns to provide depth information. In order to improve the visual quality of captured documents, we established our algorithm from two perspectives. First, we deal with the shading situation in the captured image as a result of the non-uniform lighting condition. The shading correction is based on the shading information of the margin of the document, or based on the estimated relative position of each piece of the scanned open book to the active illumination. The open book will look like it is captured under a uniform lighting source in the corrected images. Next, we handle the geometric distortion. The 3D shape reconstruction methods and geometric rectification are used to flatten the curvature of an open book. The models we used exploit specific prior assumptions about the nature of the printed material that is captured. The warped text line can be straightened after this rectification. The overall readability improvement in captured open book images obtained by using our method can be observed in the experimental results.

Degree

Ph.D.

Advisors

Allebach, Purdue University.

Subject Area

Computer Engineering|Electrical engineering

COinS