In video surveillance, identification is a very significant element for target tracking, activity recognition, traffic monitoring, military etc. The identification process classifies the pixels into either foreground or background and a common approach used to achieve such a classification is background removal. A Novel method is proposed for the moving object detection based on Modular Wavelet...

Tabla, a percussion instrument, mainly used to accompany vocalists, instrumentalists and dancers in every style of music from classical to light in India, mainly used for keeping rhythm. This percussion instrument consists of two drums played by two hands, structurally different and produces different harmonic sounds. Earlier work has done labeling tabla strokes from real time performances by t...

Digital video watermarking has been widely used technology for copyright protection of the digital media. It prevents the illegal distribution of the digital data. Watermarking is the process of embedding some information in the digital media and then transmitting it. The extraction of this watermark will indicate the originality of the digital data. The additional information could be very eas...

This paper presents the hiding of text in video using haar wavelet transform in particular frame and BCH codes. Haar wavelet transform is applied to get the low frequency sub-band in an image to hide data. The frequency sub-bands are (LL, LH, HL and HH). BCH codes are used to encrypt the data. The work of various researchers is discussed about video steganography and their techniques for embedd...

The usage of ultrasound imaging for medical diagnosis is limited due to the presence of speckle noise. In this study Modified Adaptive Wavelet Shrinkage Filter (MAWSF) in the translational invariant domain is proposed for the removal of speckle noise. The adaptive wavelet threshold function removes the fixed bias of soft thresholding. A new inter-scale dependency model is proposed, to perform a...

We are concerned with the development of effective training strategies for light-weight deep networks, which facilitates harnessing power learning on hand-held devices. A vast literature has focused enhancing performance convolution models (CNNs) by introducing changes in model architecture and/or developing new procedures. Recent witnessed a growing focus pooling layers, one example this is wa...

An image compression algorithm based on wavelet packet transform is introduced. The algorithm extends the parent-children link established across dyadic wavelet decomposition bands to a parent-children link across wavelet packet decomposition bands. Then, a method proposed for the efficient encoding of dyadic wavelet transform coefficients [1] is used for encoding of wavelet packet transform co...

In this paper, a digital image watermarking technique combining Discrete Wavelet Transform (DWT) and Discrete Fractional Fourier Transform (DFRFT) has been investigated. This is a non-blind watermarking technique that exploits multi-resolution sub-band decomposition property of DWT and applies DFRFT on selected sub-bands in DWT-transformed image. The performance of this algorithm under various ...

The paper presents a prototype of power quality disturbance recognition system. The prototype contains two main components: a simulator to generate power quality disturbances and a classifier to identify these disturbances. Based on the results of site measurements, the disturbance generator is designed to simulate different power quality disturbances frequently encountered at power system sub-...