Study on texture feature extraction from forensic images with watermark
Ying Liu, Zong Li · 2014
In order to protect the legitimacy and integrity of Criminal Scene Investigation image data, digital watermark can be embedded into the images, as evidence of identification of illegal infringement. This paper studies on texture feature extraction from forensic tyre tread patterns with watermark, in order for automatic tyre tread pattern retrieval. Intensive literature survey shows that this work is the first on feature extraction from forensic images with watermark. A new Tamura feature extraction algorithm is presented and compared with state-of-the-art texture feature extraction methods. Experimental results demonstrate the promising performance of the proposed algorithm in forensic tyre tread pattern image retrieval.