Some works are reported in the frequency domain watermarking using Single Value Decomposition (SVD). The two most commonly used methods are based on DCT-SVD and DWT-SVD. The commonly present disadvantages in traditional watermarking techniques such as inability to withstand attacks are absent in SVD based algorithms. They offer a robust method of watermarking with minimum or no distortion. DCT based watermarking techniques offer compression while DWT based compression offer scalability. Thus all the three desirable properties can be utilized to create a new robust watermarking technique. In this paper, we propose a method of non-blind transform domain watermarking based on DWT-DCT-SVD. The DCT coefficients of the DWT coefficients are used to embed the watermarking information. This method of watermarking is found to be robust and the visual watermark is recoverable without only reasonable amount of distortion even in the case of attacks. Thus the method can be used to embed copyright information in the form of a visual watermark or simple text.

Face is the primary index for imparting the identity. Automated face detection is one of the interesting field of research. Face detection of digital image has acquired much importance and interest in last two decades, which has applications in different fields. Computerizing the process needs many image processing methods. In this paper, a new face detection approach using color base segmentation and morphological operations is presented. The algorithm uses color plane extraction, background subtraction, thresholding, morphological operations(such as erosion and dilation ), filtering (to avoid false detection). Then particle analysis is done to detect only the face area in the image and not the other parts of the body. The color planes are extracted using vision module the RGB color space is converted into suitable color space such as HSV and YCbCr. The algorithm can be used to detect both single as well as multiple persons in a image. Experimental results of the algorithm show that , it is good enough to detect the human faces with an accuracy of 93% i.e., the efficiency of the detection is up to 93%.

No abstract

No abstract