An Optimized Deep Fusion Convolutional Neural Network-Based Digital Color Image Watermarking Scheme for Copyright Protection

• Published in: Circuits, systems, and signal processing Vol. 42; no. 7; pp. 4019 - 4050
• Main Authors: Rai, Manish, Goyal, Sachin, Pawar, Mahesh
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.07.2023; Springer Nature B.V
• Subjects: Algorithms; Artificial neural networks; Bit error rate; Blurring; Circuits and Systems; Codes; Color imagery; Digital imaging; Electrical Engineering; Electronics and Microelectronics; Embedding; Engineering; Feature extraction; Instrumentation; Multimedia; Neural networks; Optimization; Redundancy; Robustness; Signal to noise ratio; Signal,Image and Speech Processing; Watermarking; Deep learning; Imperceptibility; Color images; Digital image watermarking; Copyright protection; Robustness; Optimization
• ISSN: 0278-081X; 1531-5878
• DOI: 10.1007/s00034-023-02299-1

The active use of the Internet and multimedia content has recently escalated copyright violations. Digital content, especially images and videos are subject to vulnerable attacks. It is also possible that an attacker might remove the watermark from the original image. Therefore, the copyright of digital images must be secured to prevent them from being inappropriately misused. This paper proposes an Enhanced Chimp Optimization algorithm based on Deep Fusion Convolutional Neural Network (ECO-DFCNN) for robust watermarking. The proposed framework consists of an embedding and extraction network to embed and extract the watermark. The octave convolutional model introduced in the embedding network captures various features and decreases spatial redundancy. In addition, the ECO algorithm is introduced to overcome the trade-off between robustness and imperceptibility by determining the optimal strength factor. The pyramid feature extraction module in the extraction network extracts the local features and the dilated convolutions minimize the model parameters. The proposed ECO-DFCNN method is tested against various attacks such as histogram equalization, compression, cropping, scaling, blurring, and median filtering. The proposed ECO-DFCNN method is evaluated and the performance is determined by comparing the obtained results with the existing watermarking techniques. The results show that the proposed ECO-DFCNN watermarking method is robust against various attacks while maintaining excellent imperceptibility with a high Peak Signal-to-Noise Ratio of 54.64 dB, Normalized Correlation of 0.98 and Structural Similarity Index Measure of 0.97, and low Bit Error Rate of 0.038.