Optimizations using the genetic algorithm for reversible watermarking

• Published in: 2013 10th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology pp. 1 - 5
• Main Authors: Panyindee, Chaiyaporn, Pintavirooj, Chuchart
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01-05-2013
• Subjects: Biological cells; expanded variance mean; Gaussian weight predictor; genetic algorithm; Genetic algorithms; Payloads; Prediction algorithms; Prediction error (PE); PSNR; Sorting; Watermarking
• ISBN: 9781479905461; 1479905461
• DOI: 10.1109/ECTICon.2013.6559504

Important requirements for reversible data hiding techniques: the embedding capacity should be large and distortion should be low. This paper represents a high performance reversible watermarking technique which involves adaptable predictor and sorting parameter to suit each image and each payload in order get lowest image distortion. Our proposed method relies on a well-known prediction error (PE) expansion technique. Having small PE values and a harmonious PE sorting parameter will greatly decrease distortion. In order to get adaptable tools, Gaussian weight predictor and expanded variance mean were used as parameters in this work. A genetic algorithm has also been introduced to optimize all parameters and produce the best results possible. Implementation showed a significantly improved result compared to previous work.