A Two Layer Approach to Image Authentication and Encryption through ECC & Voice Features (MFCC, Pitch Value)
Vikas Pardesi1, N. S. Raghava2
1Vikas Pardesi, Dept. of Information Technology, Delhi Technology University, Delhi, India.
2N. S. Raghava, Dept. of Information Technology, Delhi Technology University, Delhi, India.
Manuscript received on March 02, 2013. | Revised Manuscript received on April 13, 2013. | Manuscript published on April 30, 2013. | PP: 472-478 | Volume-2, Issue-4, April 2013. | Retrieval Number: D1483042413/2013©BEIESP
Open Access | Ethics and Policies | Cite
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Speech Processing is an area in which we can find such unique features (Mel Frequency Cepstrum Coefficients, Pitch value, zero crossing rates etc.) in voice segment for recognition of any individual and pre-processing for further synthesis. In this paper we are presenting a simplified approach to image authentication with MFCC (Mel Frequency Cepstrum Coefficients) and Pitch Value and image Encryption through Elliptic Curve Cryptography. Because of ECC great advantages (small key size, no solution to discrete logarithmic problem, less time consuming encryption, infinite time taken for brute force attack) for handheld, portable devices. Applying MFCC and Pitch information with various methods on various encrypted images which is encrypted by Elliptic Curve Cryptography and at the receiver side we do reverse process of this approach for authentication and decryption of image .With this approach we can authenticate an image through voice segment which is advantageous because speech is a natural way to interact with people, Not required to sit and work with a keyboard and finally no specific training is required for end users.
Keywords: Elliptic curve cryptography, MFCC, Pitch value, public key cryptography, Speech Processing.