Application of Digital Fingerprinting: Duplicate Image Detection

Maharana, Ashutosh (2016) Application of Digital Fingerprinting: Duplicate Image Detection. MTech thesis.

[img]
Preview
PDF
572Kb

Abstract

Identifying the content automatically is the most necessary condition to detect and fight piracy. Watermarking the image is the most basic and common technique to fight piracy. But the effectiveness of watermark is limited. Image fingerprinting provides an alternate and efficient solution for managing and identifying the multimedia content. After registering the original image contents, by comparing the colluded image with the original one, the percentage of distortion can be calculated. In this paper presented are one such fingerprinting-based forensic application: Duplicate image detection. To authenticate image content perceptual hash is an efficient solution. Perceptual hashes of almost similar images or near duplicate images are very similar to each other making it easier to compare images unlike cryptographic hashes which vary very radically even in the case of small distortions. Potential applications are unlimited including digital forensics, protection of copyrighted material etc. However, conventional image hash algorithms only offer a limited authentication level for the protection of overall content. In this work, we compared and contrasted different perceptual hashes and proposed a image hashing algorithm which is an excellent trade off of accuracy and speed.

Item Type:Thesis (MTech)
Uncontrolled Keywords:Digital Fingerprint; Image Hashing Algorithm; Perceptual Hash
Subjects:Engineering and Technology > Computer and Information Science > Image Processing
Engineering and Technology > Computer and Information Science > Information Security
Divisions: Engineering and Technology > Department of Computer Science
ID Code:8279
Deposited By:Mr. Sanat Kumar Behera
Deposited On:15 Dec 2016 14:44
Last Modified:15 Dec 2016 14:44
Supervisor(s):Naskar, R

Repository Staff Only: item control page