Title: Image restoration with broken curve prediction

Authors: Hwei-Jen Lin, Chun-Wei Wang, Yuan-Chun Hsieh, Yang-Ta Kao

Addresses: Department of Computer Science and Information Engineering, Tamkang University, 151 Ying-chuan Rd., Tamsui, Taipei County, Taiwan 25137, Republic of China. ' Department of Computer Science and Information Engineering, Tamkang University, 151 Ying-chuan Rd., Tamsui, Taipei County, Taiwan 25137, Republic of China. ' Department of Computer Science and Information Engineering, Tamkang University, 151 Ying-chuan Rd., Tamsui, Taipei County, Taiwan 25137, Republic of China. ' Department of Information Network Technology, ChihLee Institute of Technology, No. 313, Sec. 1, Wunhua Rd., Banciao City, Taipei County, Taiwan 220, Republic of China

Abstract: In this paper, a new approach is presented for the restoration of missing or damaged portions of an image. The algorithm first locates several feature points on the boundary of the damaged region of a given image. Broken curves are then automatically predicted and reconstructed by using the B-spline functions. Finally, a method that combines the advantages of texture synthesis and image inpainting is applied to restore the remaining damaged portion. Several experimental results provided demonstrate the achievements of the proposed technique.

Keywords: image inpainting; image restoration; texture synthesis; B-spline; interpolation; broken curves; image damage; computational vision.

DOI: 10.1504/IJCVR.2009.026830

International Journal of Computational Vision and Robotics, 2009 Vol.1 No.1, pp.110 - 120

Published online: 26 Jun 2009 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article