An Inpainting- Based Deinterlacing Method

Video is usually acquired in interlaced format, where each image frame is composed of two image fields, each field holding same parity lines. However, many display devices require progressive video as input; also, many video processing tasks perform better on progressive material than on interlaced video. In the literature, there exist a great number of algorithms for interlaced to progressive video conversion, with a great tradeoff between the speed and quality of the results. The best algorithms in terms of image quality require motion compensation; hence, they are computationally very intensive. In this paper, we propose a novel de interlacing algorithm based on ideas from the image in painting arena. We view the lines to interpolate as gaps that we need to in paint. Numerically, this is implemented using a dynamic programming procedure, which ensures a complexity of O(S), where S is the number of pixels in the image. The results obtained with our algorithm compare favorably, in terms of image quality, with state-of-the-art methods, but at a lower computational cost, since we do not need to perform motion field estimation.

[1]  Jean-Michel Morel,et al.  Level lines based disocclusion , 1998, Proceedings 1998 International Conference on Image Processing. ICIP98 (Cat. No.98CB36269).

[2]  Yrjö Neuvo,et al.  Improving TV picture quality with linear-median type operations , 1988 .

[3]  Patrick Pérez,et al.  Region filling and object removal by exemplar-based image inpainting , 2004, IEEE Transactions on Image Processing.

[4]  Simon Masnou,et al.  Disocclusion: a variational approach using level lines , 2002, IEEE Trans. Image Process..

[5]  A.W. Morales,et al.  Spatio-temporal edge-based median filtering for deinterlacing , 2000, 2000 Digest of Technical Papers. International Conference on Consumer Electronics. Nineteenth in the Series (Cat. No.00CH37102).

[6]  Changming Sun,et al.  De-interlacing of video images using a shortest path technique , 2001, IEEE Trans. Consumer Electron..

[7]  Seungjoon Yang,et al.  Motion compensation assisted motion adaptive interlaced-to-progressive conversion , 2003, Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429).

[8]  Ingemar J. Cox,et al.  A Maximum Likelihood Stereo Algorithm , 1996, Comput. Vis. Image Underst..

[9]  Hoon Yoo,et al.  Direction-oriented interpolation and its application to de-interlacing , 2002, IEEE Trans. Consumer Electron..

[10]  Harry Shum,et al.  Full-frame video stabilization , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[11]  Minglun Gong,et al.  Near real-time reliable stereo matching using programmable graphics hardware , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[12]  Mei-Juan Chen,et al.  Efficient de-interlacing technique by inter-field information , 2004, IEEE Transactions on Consumer Electronics.

[13]  Alfred M. Bruckstein,et al.  Spatial de-interlacing using dynamic time warping , 2005, IEEE International Conference on Image Processing 2005.

[14]  Arun N. Netravali,et al.  Time-recursive deinterlacing for IDTV and pyramid coding , 1990, Signal Process. Image Commun..

[15]  A. M. Bock Motion-adaptive standards conversion between formats of similar field rates , 1994, Signal Process. Image Commun..

[16]  Bernard Besserer,et al.  High Quality deinterlacing using Inpainting and shutter-Model Directed Temporal interpolation , 2004, ICCVG.

[17]  Weiguo Liu,et al.  Bio-sequence database scanning on a GPU , 2006, Proceedings 20th IEEE International Parallel & Distributed Processing Symposium.

[18]  Eli Shechtman,et al.  Space-time video completion , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[19]  Erwin B. Bellers,et al.  Deinterlacing-an overview , 1998, Proc. IEEE.

[20]  Takahiko Fukinuki,et al.  A Motion-Adaptive High-Definition Converter for NTSC Color TV Signals , 1984 .

[21]  Chein-Wei Jen,et al.  Motion detection and motion adaptive pro-scan conversion , 1991, 1991., IEEE International Sympoisum on Circuits and Systems.

[22]  Jelena Kovacevic,et al.  Deinterlacing by successive approximation , 1997, IEEE Trans. Image Process..

[23]  Liang-Gee Chen,et al.  Four field local motion compensated de-interlacing , 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[24]  Sung Yong Shin,et al.  On pixel-based texture synthesis by non-parametric sampling , 2006, Comput. Graph..

[25]  Thomas Christopher,et al.  Interlace to progressive scan converter for IDTV , 1992 .

[26]  Gerard de Haan,et al.  Motion estimation on interlaced video , 2005, IS&T/SPIE Electronic Imaging.

[27]  Liang-Gee Chen,et al.  Four field variable block size motion compensated adaptive de-interlacing , 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

[28]  오승준 [서평]「Digital Video Processing」 , 1996 .

[29]  Guillermo Sapiro,et al.  Simultaneous structure and texture image inpainting , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[30]  Simon Masnou Filtrage et désocclusion d'images par méthodes d'ensembles de niveau , 1998 .

[31]  Gerard de Haan,et al.  On video formats and coding efficiency , 1999, 1999 Digest of Technical Papers. International Conference on Consumer Electronics (Cat. No.99CH36277).

[32]  Yrjö Neuvo,et al.  Fractional frame rate up-conversion using weighted median filters , 1989 .

[33]  Jeong-Sang Lee,et al.  A new algorithm for interlaced to progressive scan conversion based on directional correlations and its IC design , 1994 .

[34]  Bellers,et al.  De-interlacing Video Data , 1997, 1997 International Conference on Consumer Electronics.

[35]  Masahiko Achiha,et al.  High Quality Digital TV With Frame Store Processing , 1987, IEEE Transactions on Consumer Electronics.