In this report, we deal with two challenges when building a real-world face recognition system the pose variation in uncontrolled environment and the computational expense of processing a video stream. First, we argue that the frame-wise feature mean is unable to characterize the variation among frames. We propose to preserve the overall pose diversity if we want the video feature to represent ...

•Finds regions of quiet speech using the noise estimate and scales these regions using α = 0.99 to avoid noise amplification for low SNR’s •Identifies if the high amplitudes of the frame will be clipped after scaling and reduces the scale factors accordingly Key Aspects of the Volume Leveler •Tracks the noise level when the Voice Activity Detector(VAD) does not detect speech, so pure noise regi...

We consider the problem of testing for the presence (or detection) of an unknown sparse signal in additive white noise. Given a fixed measurement budget, much smaller than the dimension of the signal, we consider the general problem of designing compressive measurements to maximize the measurement signal-to-noise ratio (SNR), as increasing SNR improves the detection performance in a large class...

My research aims at the decoding of purely compressed-sensed videos sequences. In my major work of Ph.D. studies, I considered block-based CS video transmission systems. In such systems, the transmitter/encoder partitions each video frame into non-overlapping blocks, and performs nothing more than compressed sensing acquisition of each block independently, without the benefits of the familiar s...

We investigate the spectrum for frames with block size four, and discuss several applications to the construction of other combinatorial designs. Our main result is that a frame of type hu, having blocks of size four, exists if and only if u ≥ 5, h ≡ 0 mod 3 and h(u − 1) ≡ 0 mod 4, except possibly where (i) h = 9 and u ∈ {13, 17, 29, 33, 93, 113, 133, 153, 173, 193}; (ii) h ≡ 0 mod 12 and u ∈ {...

INTRODUCTION: First-pass cardiac perfusion MRI requires fast data acquisition to achieve an appropriate combination of temporal resolution, spatial resolution and spatial coverage for clinical studies [1]. We have recently presented a combination of compressed sensing and parallel imaging (k-t SPARSE-SENSE) to highly accelerate perfusion studies by jointly exploiting sparsity in the combined sp...

In several applications, MRI is used to monitor the time behavior of the signal in an organ of interest; e.g., signal evolution because of physiological motion, activation, or contrast-agent accumulation. Dynamic applications involve acquiring data in a k-t space, which contains both temporal and spatial information. It is shown here that in some dynamic applications, the t axis of k-t space is...

‎‎The tensor product is the fundemental ingredient for extending one-dimensional techniques of filtering and compression in signal preprocessing to higher dimensions‎. ‎Woven frames play ‎ a crucial role in signal preprocessing and distributed data processing‎. Motivated by these facts, we have investigated the tensor product of woven frames and presented some of their properties. Besides...

Visual sensor networks (VSNs) usually generate a low-resolution (LR) frame-sequence due to energy and processing constraints. These LR-frames are not very appropriate for use in certain surveillance applications. It is very important to enhance the resolution of the captured LR-frames using resolution enhancement schemes. In this paper, an effective framework for a super-resolution (SR) scheme ...

Due to the sheer volume of data involved, video coding is an important application of lossy source coding, and has received wide industrial interest and support as evidenced by the development and success of a series of video coding standards. All MPEG-series and H-series video coding standards proposed so far are based upon a video coding paradigm called predictive video coding, where video so...