• Randheer Bagi
• Tanima Dutta
• Hari Prabhat Gupta

The perceptual hash dependent on the content of the multime-dia object is widely used to protect from copy attack, a wa-termark estimation attack, that causes protocol ambiguity in a watermarking system. Frame averaging is mainly used for watermark estimation. Motion coherency is essential to resist temporal frame averaging. Compressed domain techniques have less complexity as full decoding and re-encoding is not required. As far we know, no perceptual hash based on motion coherency especially in compressed domain is yet explored. Our main contributions are: 1) motion coherent macroblocks are detected in compressed domain; 2) a perceptual hash is extracted from robust compressed domain features, like, lu-minance intra prediction modes, zero or nonzero value DC coefficients and chrominance modes of motion coherent mac-roblocks; 3) finally, the robustness of motion coherent percep-tual hash is experimentally verified against different attacks. A feature based comparative study and time complexity of our method are also discussed.

Compressed domain, perceptual hash, motion coherent, copy attack, temporal frame averaging

"PERCEPTUAL HASH FOR COMPRESSED MEDICAL VIDEO", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 2, page no.1-5, February-2019, Available :http://www.jetir.org/papers/JETIRAB06001.pdf

"PERCEPTUAL HASH FOR COMPRESSED MEDICAL VIDEO", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 2, page no. pp1-5, February-2019, Available at : http://www.jetir.org/papers/JETIRAB06001.pdf