Open Access Open Access  Restricted Access Subscription or Fee Access

An Automatic Restoration Framework for Image Enhancement

C. Karpagavalli, R. Ramani

Abstract


An automatic restoration system targeting on dirt and blotches in images has crucial challenges in the aspect of achieving accuracy in Defect Detection and Removal process. Algorithms developed till date suffer from many false alarms and need two stage false alarm elimination process and also limit the expressiveness of the images and only crudely capture the statistics of natural images. The proposed system poses remedies for problems associated with the existing systems. In general, an automatic restoration system contains two stages named as detection of defects and removal of degraded pixels. Adaptive histogram shape based thresholding algorithm is used for creating defect map for finding the degraded pixel which ensures that there will be no false alarm generation. Next, the quality of degraded pixels will be enhanced by using Field of Experts method. This process preserves the expressiveness of the original images and exactly captures the statistics of natural images. The performance will be measured by computing the quality measures such as PSNR and MSE. Finally, experiment results show that the proposed algorithm guarantees the accuracy and efficiency of defect detection and removal processing.

Keywords


Archive Film Restoration, Defect Detection, Defect Removal, Adaptive Histogram Shape Based Thresholding, Field of Experts

Full Text:

PDF

References


Xiaosong Wang and Majid Mirmehdi,‖Archive Film Defect detection and Removal:An Automatic Restoration Framework‖ IEEE Trans. Image Process., vol. 21, no. 8, pp. 882–889, Aug. 2012.

J. Ren and T. Vlachos, ―Efficient detection of temporally impulsive dirt impairments in archived films,‖ Signal Process., vol. 87, no. 3, pp. 541– 551, 2007.

L. Grady, ―Random walk for image segmentation,‖ IEEE Trans. Pattern Anal. Mach. Intell., vol. 28, no. 11, pp. 1768–1783, Nov. 2006.

Y. Wexler, E. Shechtman, and M. Irani, ―Space-time video completion,‖ in Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., vol. 1. Jun. 2004, pp. 120–127.

M. Bertalmio, L. Vese, G. Sapiro, and S. Osher, ―Simultaneous structure and texture image inpainting,‖ IEEE Trans. Image Process., vol. 12, no. 8, pp. 882–889, Aug. 2003.

A. Criminisi, P. Pérez, and K. Toyama, ―Region filling and object removal by exemplar-based image inpainting,‖ IEEE Trans. Image Process., vol. 13, no. 9, pp. 1–13, Sep. 2004.

S.-C. Nam, M. Abe, and M. Kawamata, ―Fast and efficient MRFbased detection algorithm of missing data in degraded image sequences,‖ IEICE Trans. Fundam. Electron., Commun. Comput. Sci., vol. E91.A, no. 8, pp. 1898–1906, 2010.

M. Chong and D. Krishnan, ―An edge-preserving MRF model for the detection of missing data in image sequences,‖ IEEE Signal Process. Lett., vol. 5, no. 4, pp. 81–83, Apr. 1998.

R. Bornard, E. Lecan, L. Laborelli, and J.-H. Chenot, ―Missing data correction in still images and image sequences,‖ in Proc. 10th ACM Int. Conf. Multimedia, 2002, pp. 355–361.

A. Cuzol, K. S. Pedersen, and M. Nielsen, ―Field of particle filters for image inpainting,‖ J. Math. Imag. Vis., vol. 31, nos. 2–3, pp. 147–156, 2008.

A. Koaram, R. Morris, W. Fitzgerald, and P. Rayner, ―Interpolation of missing data in image sequences,‖ IEEE Trans. Image Process., vol. 4, no. 11, pp. 1509–1519, Nov. 1995.

J. Y. Bouguet, ―Pyramidal implementation of the lucas kanade feature tracker,‖ Miroprocessor Research Laboratories, Intel Corporation, Santa Clara, CA, Tech. Rep., 2000.


Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.