Browsing by Author "Jayamalar, T"

Now showing 1 - 14 of 14
  • No Thumbnail Available
    Item
  • No Thumbnail Available
    Item
    Audio Watermarking System Using EMD with Psyehoacoustic Model
    (2013) Jayamalar, T
    A new adaptive audio watermarking algorithm based on empirical mode decomposition (EMD) with human aiiditoi7 and psychoacoustic model is used in this I'esearch. The audio signal is divided into frames and each one is decomposed adaptively, by EMD, into intrinsic oscillatory components called Intrinsic Mode Functions (IMFs). The watermark and the synchronization codes are embedded into the extrema of the last IMF, a low frequency mode stable under different attaclis and presei'ving audio |)erceptual quality of the host signal. The data embedding rate of tbe EMD algorithm is 46.9-50.3 b/s. Relying on exhaustive simulations, show the robustness of the hidden watermark for additive noise, MP3 compression, re-quantization, fdtering, cropping and resampling. Empirical Mode Decomposition (EMD) has been introduced for analyzing nonstationai7 signals derived or not from linear systems in totally adaptive way. A major advantage of EMD relies on no a priori choice of fdtei'S or basis functions. EMD is fully data-driven metbod that reciii-sively breaks down any signal into a reduced number of zero-mean with symmetric envelo|)es AM-FM components called Intrinsic Mode Functions (IMFs). The decomposition starts from finer scales to coaiser ones. The psychoacoustic model is basically based on many studies of human auditory perception. In this research, the watermark in audio can be embedded and extracted with different techniques. The psychoacoustic model can be done before embedding the watermark bit. In the scheme, the additive watermarking technique is used to embed a unique pseudo- random sequence, considered as a watermark, into the transformed domain of audio signal. The watermark strength is properly adjusted based on weighting factors derived from the proposed psyehoacoustic models. The results show that at the equivalent quality of the watermarked audio, judged by tbe human hearing system, the robustness of the embedded watermark was increased to higher liercentage, compared to the results obtained from tbe scheme with non- psyehoacoustic model and the [isyclioacoiistic model.
  • No Thumbnail Available
    Item
  • No Thumbnail Available
    Item
    Email Spam Detection using Supervised Learning
    (2023-05) Vaishnavi, K; Jayamalar, T
  • No Thumbnail Available
    Item
    Enhanced Nested Video Watermarkin g Using Waveletsan D Geometric Warping
    (2011) Jayamalar, T
    The amount of information created in the current era of information explosion is increasing in a overwhelming fashion. This increase in content has increased the awareness to protect the intellectual property. This paper presents one such method to protect Video content. The proposed watermarking hybrid scheme combines visual cryptography and wavelets to create a nested watermark, which is embedded into the raw uncompressed video signal using geometric warping technology. A block selection algorithm is used to select relevant area for embedding so as to improve robustness. The experimental results showed that the proposed system shows significant improvement in terms of capacity and robustness against various attacks.
  • No Thumbnail Available
    Item
    Enhanced Wavelet Packet Based un Compressed Video Watermarking Algorithm With Frame Selection and Hvs Criteria
    (2014) Jayamalar, T
    Digital video is a group of moving visual images, text and sounds. The popularity of using digital video in Internet leads to illicit copying and dispersal of content. In order to avoid this, video watermarking technique are used as a preventive measure for illegal copying of copyrighted material. In this paper, watermarking algorithm for identification of optimal frames and embedding of nested watermark using static block selection is proposed. The nested watermark is embedded in the uncompressed video data and is extracted without the use of original video sequences. These algorithms preserve the video quality and provide more security. The performance of the algorithm is analyzed using Peak Signal to Noise Ratio, Normalized Correlation and Mean structure similarity index with respect to various attacks. Experimental evaluation demonstrate that the proposed algorithm perform satisfactorily compared to traditional algorithms in terms of payload, transparency and it is also robust against various attacks.
  • No Thumbnail Available
    Item
    Forest Fire Detection Using Image Processing Techniques
    (2021-05) Razina, A; Jayamalar, T
  • No Thumbnail Available
    Item
    Improved Video Watermarking using Nested Watermark, Wavelets and Geometric Warping
    (2011) Jayamalar, T
    The advancements in communication software and hardware is increasing the amount of information in the form of text, image, audio and video being shared. This increase arise the issue of protecting the intellectual property. This paper studies the protection of video signals through watermarking. The system proposed uses a combination of visual cryptography and wavelets to create a nested watermark which is embedded into the raw uncompressed video signal using a geometric warping technology. To improve robustness against compression, the method embeds the watermark in relevant area using a block selection method. The experimental results prove that the proposed system is efficient in terms of capacity and robustness against various attacks.
  • No Thumbnail Available
    Item
  • No Thumbnail Available
    Item
    Rainfall Prediction Using Machine Learning Algorithms
    (2021-05) Iswarya, P; Jayamalar, T
  • No Thumbnail Available
    Item
    A Study on Video Watermarking Techniques
    (2010) Jayamalar, T
    Digital video is becoming popular more than ever due to- the widespread o f video-based applications such as Internet video, video phones, wireless video, video conferencing among many others. However, a byproduct o f such popularity is the worldwide unauthorized copying and distribution o f digital video. This creates a high demand for content protection technique like video watermarking. In this paper, a brief reyie^ o f current video watermarking technologies is presented.
  • No Thumbnail Available
    Item
    Survey on Digital Video Watermarking Techniques and Attacks on Watermarks
    (2010) Jayamalar, T
    Digital video watermarking is a technique for embedding additional data along with video signal. Embedded data is used for copyright owner identifieation. A number of video watermarking techniques are proposed. These techniques exploit different ways in order to embed a robust watermark and to maintain the original video signal fidelity. In this paper. Digital video watermarking techniques and attacks on watermarks are presented.
  • No Thumbnail Available
    Item
    Video Watermarking using Wavelet Packets and Block Selection Technique
    (2011) Jayamalar, T
    Digital video watermarking has fascinated a great deal of research interest in the past few years in applications such as copyright protection, digital fingerprinting and owner identification. In this paper, a combined video watermarking scheme is proposed based on wavelet packets and block selection technique. The performance of the proposed video watermarking algorithm is measured in terms of normalized cross correlation. Further, this combined scheme provides good experimental results against temporal attacks such as frame averaging, frame dropping and compression.
  • No Thumbnail Available
    Item
    Video Watermarking Using Wavelet Packets and Block Selection Technique
    (2011) Jayamalar, T
    Digital video watermarking has faseinated a great deal ofreseareh interest in the past few years in applications such as copyright protection, digital fingerprinting and owner identification. In this paper, a combined video watermarking scheme is proposed based on wavelet packets and block selection technique. The performance of the proposed video watermarking algorithm is measured in terms of normalized cross correlation. Further, this combined scheme provides good experimental results against temporal attacks such as frame averaging, frame dropping and compression.