An Image Digital Watermarking Method Based On Ridgelet and KICA

This paper presents a novel image digital watermarking method combined the Ridgelet transform with Kernel Independent Component Analysis (KICA). Use the nice characteristic of the KICA, which can results the blind separation of nonlinearly mixed signals, the imperceptibility and robustness requirements of watermarks are fulfilled and optimized. In the proposed method, the watermark image is first transformed by Arnold scrambling method, and then embedded into the lowest frequency subband in Ridgelet transform domain. The recovery of owner's image is turning the watermarked image into Ridgelet transform domains then use KICA to extract the watermark. Finally the watermark is transformed by Arnold method again, so we can get the original watermark image. Experimental results show that the proposed method gains better performance in robustness than the before method with respect to traditional image processing including speckle attack, add noise and JPEG image compression etc.