Laser & Optoelectronics Progress, Volume. 58, Issue 6, 615006(2021)
Robust Watermarking Algorithm Based on Structured Forests Edge and SIFT
To balance the vision imperceptibility and robustness of a watermark and address copyright protection and content authentication issues in digital multimedia products, this study proposes a robust watermarking algorithm that is based on structured forests edge and the scale invariant feature transform (SIFT). First, a color image is converted from an RGB space to a Lab space, and the 1024 stable SIFT points are extracted based on an L component as the embedding position of watermark. Second, the image edge is extracted using a trained random decision forest model as the watermark image that is decomposed by the discrete wavelet transform (DWT) to obtain a low-frequency sub-band that is divided into nonoverlapping blocks. The maximum values of the blocks are obtained and encrypted using the Arnold transform. Experimental results show that the proposed algorithm exhibits better imperceptibility and robustness to resist various attacks, such as cropping, speckle noise, and motion blur, in comparison with other related algorithms. Furthermore, it effectively protects the original edge features of an image.
Get Citation
Copy Citation Text
Liu Ying, Yang Xing, Zhu Tingge. Robust Watermarking Algorithm Based on Structured Forests Edge and SIFT[J]. Laser & Optoelectronics Progress, 2021, 58(6): 615006
Category: Machine Vision
Received: Jul. 21, 2020
Accepted: --
Published Online: Mar. 11, 2021
The Author Email: Xing Yang (1830850314@qq.com)