Enhanced Decoding Based on Authenticating the Region of Interests
In this chapter, a method for image authentication is described which also supports enhanced decoding. The method works in two steps at the receiver. In the first step only important parts of image are authenticated. The important parts are pre-marked regions of importance in the image such as the retina of an eye, number plate of a car. When the first phase succeeds, the second phase follows. In the second step, the successfully authenticated pre-marked important segments are used for improved decoding of the image. For this purpose, additional information is used from the channel as a side information. It is shown that the results produced by the two-phase method are superior both for authentication as well as for error correction.
KeywordsAuthentication Decoding Two-step decoding Error correction Forgery detection
- 1.C. Ruland, N. Zivic, Soft Input Decryption, 6th International ITG Conference on Source and Channel Coding, Apr. 3–7, 2006, Munich, GermanyGoogle Scholar
- 2.C. Berrou, A. Glavieux, P. Thitimajshima, Near Shannon Limit Error Correcting Coding and Decoding: Turbo-Codes. 1. IEEE International Conference on Communications (ICC '93), May 23–26, 1993, Geneva, SwitzerlandGoogle Scholar
- 3.C. Ruland, N. Živic, Feedback in Joint Coding and Cryptography. 7th International ITG / IEEE Conference on Source and Channel Coding, January 2008, Ulm, GermanyGoogle Scholar
- 5.Y T. Zheng, M. Zhao, Y. Song, H. Adam, U. Buddemeier, A. Bissacco, F. Brucher, T. Chua, Tour the World: Building a Web-Scale Landmark Recognition Engine. 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, 2009, pp. 1085–1092Google Scholar