Please use this identifier to cite or link to this item: http://dspace.dtu.ac.in:8080/jspui/handle/repository/14622
Title: A TWO LAYER IMAGE AUTHENTICATION & ENCRYPTION SCHEME THROUGH ECC & VOICE FEATURES (MFCC, PITCH VALUE)
Authors: PARDESI, VIKAS
Keywords: IMAGE AUTHENTICATION
ENCRYPTION
SPEECH PROCESSING
MFCC
ECC
Issue Date: Apr-2016
Series/Report no.: TD NO.1255;
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. Image processing is a branch of Computer Science in which we study about images and its processing for further additional improvements in the images. When we apply speech details in the image then our image get distracted and forms a new image and then we transfer it in the network by this we can do two types of work in the image processing area first one is we can authenticate an image and second one is encryption of the image because when we receive the image on receiver side then we can apply the same voice on image and apply reverse operation and can find the same image and after decryption of image we get the original image. In speech processing area there are such features of voice as pitch frequency and fundamental frequency and MFCC coefficients and many other features that are unique. On this basis we can use these features to process out in any field with other one in detail. v Applications and usage of this proposed system is to make our data transferring more authenticated and encrypted through latest technology i.e. elliptic curve cryptography. Now days secure data transmission is the main challenge of our priority. In this proposed system we are just providing the external schema of the authentication and encryption detail .we are not considering any kind of complexity comes under the authentication protocols. Due to this proposed system we can make our system and data more secure and added another step to security of the data in the network.
URI: http://dspace.dtu.ac.in:8080/jspui/handle/repository/14622
Appears in Collections:M.E./M.Tech. Information Technology

Files in This Item:
File Description SizeFormat 
VIKAS PARDESI THESIS REPORT 2k11 isy 21.pdf1.99 MBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.