Image watermarking approach of criminal face authentication with recovery for detecting exact criminal

This paper introduces a watermarking approach of detecting exact criminal from the received criminal photograph by criminal investigation department. As in criminal photograph, criminal face is the region of interest (ROI) part, the bits of binary logo of criminal investigation department are embedded into the criminal face as authentication information or the watermark. Before embedding, the logo is scrambled by using the generations of game of life cellular automaton. At the same time, information of criminal face is also embedded into region of non-interest (RONI) part of criminal photograph for the recovery process. Based on discrete wavelet transform (DWT), information of criminal face is embedded into the coefficients of transformed RONI. At the receiving end, at first the logo of criminal investigation department is extracted from the criminal face of received criminal photograph. If the extracted logo or authentication information is not same as the embedded logo, the information of criminal face is only then extracted from RONI. The proposed approach is evaluated by using mean squared error (MSE), peak signal to noise ratio (PSNR) and normalized correlation (NC) performance parameters. Experimental results demonstrate that the proposed approach is secure and achieves superior face recovering accuracy. In addition, the results of the proposed method are also compared with other related existing state-of-art methods. From the results of proposed watermarking approach, it can be clearly seen that the proposed approach dominates other existing methods in MSE and PSNR values.