Watermarking Using Intelligent Methods: Survey

Watermarking Using Intelligent Methods: Survey

Channapragada R. S. G. Rao (Geethanjali College of Engineering and Technology, A. P., India), Vadlamani Ravi (Institute for Development and Research in Banking Technology (IDRBT), India), Munaga. V. N. K. Prasad (IDRBT, A. P., India) and E. V. Gopal (IDRBT, A. P., India)
Copyright: © 2014 |Pages: 10
DOI: 10.4018/978-1-4666-5202-6.ch238
OnDemand PDF Download:
$30.00
List Price: $37.50

Abstract

This chapter presents a brief review of the work done during 1990-2013, in the application of intelligent techniques to digital image watermarking. The review has mainly focused on genetic algorithms area. The review is structured by considering the type of technique applied to solve the problem as an important dimension. Comparative analysis of different techniques is presented in this paper. Finally, the review is concluded with future directions.
Chapter Preview
Top

Background

Genetic algorithms (Holland, 1975; Guo, Yang, & Li, 2003) were developed by Holland over the course of 1960s and 1970s, and finally popularized by Goldberg. These are popular for optimizing non-linear functions with multiple variables. In genetic algorithms, the parameters are represented by an encoded binary string called ‘chromosome’. The elements in the binary strings called ‘genes’ are adjusted to minimize or maximize the fitness value. The fitness function generates its fitness value, which is composed of multiple variables to be optimized by GA. It iteratively searches for an optimal solution based on fitness value using crossover, mutation and selection operators until pre-specified condition is satisfied or maximum number of iteration takes place. Due to its ability to find an optimal solution, genetic algorithms found many applications in digital image watermarking. Soft computing (Zadeh, 1994) is the state-of-art approach to artificial intelligence. Soft computing is the fusion of the fields of fuzzy logic, neural networks, evolutionary computing, and probabilistic computing and chaos theory into one multidisciplinary system. The main goal of soft computing is to develop intelligent machines and to solve nonlinear and mathematically un-modeled system problems. The term ‘soft computing’ coined by Zadeh (1994) in the early 1990s. Some of the soft computing architectures employed are neuro-fuzzy, fuzzy-neural, neuro-genetic, genetic-fuzzy, neuro-fuzzy-genetic, rough-neuro etc.

Key Terms in this Chapter

Digital Image Watermarking: This is defined as inserting authentication information into digital images.

Soft Computing: This is a term applied for defining approaches when the problem is not clear and its solution is unpredictable.

Genetic Programming: This is an evolutionary algorithm-based methodology inspired by biological evolution to find computer programs that perform a user-defined task.

Digital Watermark: A digital watermark is defined as a kind of marker covertly embedded in a noise tolerant signal such as audio or image data.

Digital Rights Management: The term refers to the protection of copyrights of digital media files, which can be implemented through encryption and decryption, steganography or digital watermarking.

Genetic Algorithms: A genetic algorithm is an experience based technique which uses fuzzy logic for solving problems.

Peak Signal To Noise Ratio: The term is defined as the ratio between the maximum possible power of a signal and the power of corrupting noise that affects the fidelity of its representation. The PSNR must be larger to have the better quality of image.

Complete Chapter List

Search this Book:
Reset