Академический Документы
Профессиональный Документы
Культура Документы
A Digital Watermarking Algorithm Based on Wavelet Packet Transform and BP Neural Network
Qiao Baoming, Zhang Pulin, Kang Qiao College of Science, Xian University of Science and Technology, Xian 710054 e-mail: qiaobm@xust.edu.cn
AbstractA new blind digital watermarking algorithm based on wavelet packet transform and BP Neural Network was proposed in this paper. The algorithm first decomposed the host image via discrete wavelet packet transform, then embedded water-marking into the position which was chosen by the key in wavelet image. In the process of embedding watermarking, eight neighborhood pixels around the embedded point was selected as sample input of the BP neural network, and the pixel value of the embedded point was chosen as the ideal output, finally, trained the neural network. Using the trained neural network, blind watermarking extraction was achieved. Keywords-component; formatting; style; styling; insert
pixels around the embedded point was selected as sample input of the BP neural network, and the pixel value of the embedded point was chosen as the ideal output, finally, trained the neural network. Using the trained neural network, blind watermarking extraction was achieved [1][11]. II.
WATERMARKING EMBEDDING ALGORITHM
A. The generation of waterarking sequences In the paper, a simple and effective method is adopted which is through the rearrangement of the binary watermark by columns, one-dimensional watermark sequence W, the size of K was obtained. B. Doing wavelet packet teansform for the original image Firstly, we did level 1 discrete wavelet transform for the original host image I, and then can get the approximate component CA, the level of detail component CH, the vertical detail component CV, and the detail of the angular component CD. This four sub-images formed Fig.1(b), Secondly, we performed level 1 discrete wavelet transform for the four components respectively. For example, After transforming CA, we obtained the approximate component CAA, the level of detail component CAH, the vertical detail component CAV, and the detail of angular component CAD. After transforming CH, the approximate component CHA, the level of detail component CHH, the vertical detail component CHV, and the detail of angular component CHD can be get; After transforming CV, the approximate component CVA, the level of detail component CVH, the vertical detail component CVV, and the detail of angular component CVD obtained, and after transforming CD, we had the approximate component CDA, the level of detail component CDH, the vertical detail component CDV, and the angular detail component CDD, The sixteen sub-images formed Fig.1(c), and Fig.1(a) is the original host image.
I.
INTRODUCTION
Digital watermarking is an important branch of the information hiding technology. The so-called digital watermarking is the digital signal which is not perceived to be embedded in digital carrier. It can be images, text, symbols, figures, and all can be used as identification information. A large number of perception redundancy part are common in multimedia data, so watermarking embedding in them can achieve the purpose of hiding. The basic idea that wavelet transform apply to image processing is decomposed the image by multi-resolution, then generate sub-image with different spaces and independent bands, at last, process the coefficients of subimage. The neural network has the characteristics of approaching non-linear mapping, and has good generalization ability. If a neural network was trained in the watermark embedding process, through studying, the corresponding relations of pixel values between before and after embedding the watermark signal is obtained, then the watermark can be extracted by using the trained neural network, thus the blind detection of the watermarking algorithm is achieved. This paper presents a new algorithm of digital watermarking based on wavelet analysis and neural network . The watermark was embedded in the wavelet image which was the host image after discrete wavelet packet transform, so that the watermarking could be embedded into a narrower and finer band, and the transparency and robustness of watermarking could be enhanced better. This algorithm decomposed the host image by discrete wavelet packet transform. Then watermarking was embedded into the position which was chosen by the key in wavelet image. In the watermarking embedding process, eight neighborhood
978-0-7695-4584-4/11 $26.00 2011 IEEE DOI 10.1109/CIS.2011.117 503