TY - JOUR
T1 - Lagrangian twin support vector regression and genetic algorithm based robust grayscale image watermarking
AU - Yadav, Ashok Kumar
AU - Mehta, Rajesh
AU - Kumar, Raj
AU - Vishwakarma, Virendra P.
N1 - Publisher Copyright:
© 2016, Springer Science+Business Media New York.
PY - 2016/8/1
Y1 - 2016/8/1
N2 - A novel imperceptible, secure and robust grayscale image watermarking scheme using Lagrangian twin support vector regression (LTSVR) and genetic algorithm (GA) in discrete Cosine transform (DCT) domain is presented in this manuscript. Fuzzy entropy is used to select the relevant blocks for embedding the watermark. Selected number of blocks based on fuzzy entropy not only reduces the dimensionality of the watermarking problem but also discards redundant and irrelevant blocks. Significant DCT coefficients having high energy compaction property of each selected block are used to form the image dataset to train LTSVR to find the non-linear regression function between the input and target vector. The adaptive watermark strength, different for each selected block, is decided by the GA process based on well defined fitness function. Due to good learning capability of image characteristics and high generalization property of LTSVR, watermark is successfully extracted from the watermarked images against a series of image processing operations. From the experimental and comparison results performed on standard and real world images, it is inferred that the proposed method is suitable for copyright protection applications where high degree of robustness is desirable.
AB - A novel imperceptible, secure and robust grayscale image watermarking scheme using Lagrangian twin support vector regression (LTSVR) and genetic algorithm (GA) in discrete Cosine transform (DCT) domain is presented in this manuscript. Fuzzy entropy is used to select the relevant blocks for embedding the watermark. Selected number of blocks based on fuzzy entropy not only reduces the dimensionality of the watermarking problem but also discards redundant and irrelevant blocks. Significant DCT coefficients having high energy compaction property of each selected block are used to form the image dataset to train LTSVR to find the non-linear regression function between the input and target vector. The adaptive watermark strength, different for each selected block, is decided by the GA process based on well defined fitness function. Due to good learning capability of image characteristics and high generalization property of LTSVR, watermark is successfully extracted from the watermarked images against a series of image processing operations. From the experimental and comparison results performed on standard and real world images, it is inferred that the proposed method is suitable for copyright protection applications where high degree of robustness is desirable.
KW - DCT
KW - Digital Image Watermarking
KW - Genetic algorithm
KW - Lagrangian Twin SVR
UR - http://www.scopus.com/inward/record.url?scp=84960096771&partnerID=8YFLogxK
U2 - 10.1007/s11042-016-3381-7
DO - 10.1007/s11042-016-3381-7
M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???
AN - SCOPUS:84960096771
SN - 1380-7501
VL - 75
SP - 9371
EP - 9394
JO - Multimedia Tools and Applications
JF - Multimedia Tools and Applications
IS - 15
ER -