Hisham Othman

Noise reduction of hyperspectral imagery using hybrid spatial-spectral derivative-domain wavelet shrinkage

In this paper, a new noise reduction algorithm is introduced and applied to the problem of denoising hyperspectral imagery. This algorithm resorts to the spectral derivative domain, where the noise level is elevated, and benefits from the dissimilarity of the signal regularity in the spatial and the spectral dimensions of hyperspectral images. The performance of the new algorithm is tested on two different hyperspectral datacubes: an Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) datacube that is acquired in a vegetation-dominated site and a simulated AVIRIS datacube that simulates a geological site. The new algorithm provides signal-to-noise-ratio improvement up to 84.44% and 98.35% in the first and the second datacubes, respectively.

A separable low complexity 2D HMM with application to face recognition

In this paper, we propose a novel low-complexity separable but true 2D Hidden Markov Model (HMM) and its application to the problem of Face Recognition (FR). The proposed model builds on an assumption of conditional independence in the relationship between adjacent blocks. This allows the state transition to be separated into vertical and horizontal state transitions. This separation of state transitions brings the complexity of the hidden layer of the proposed model from the order of (N/sup 3/T) to the order of (2N/sup 2/T), where N is the number of the states in the model and T is the total number of observation blocks in the image. The system performance is studied and the impact of key model parameters, i.e., the number of states and of kernels of the state probability density function, is highlighted. The system is tested on the facial database of AT&T Laboratories Cambridge and the more complex facial database of the Georgia Institute of Technology where recognition rates up to 100 percent and 92.8 percent have been achieved, respectively, with relatively low complexity.

Recent Developments in the Hyperspectral Environment and Resource Observer (HERO) Mission

In 1997, the Canadian Space Agency (CSA) and Canadian industry began developing enabling technologies for hyperspectral satellites. Since then, the CSA has conducted mission and payload concept studies in preparation for launch of the first Canadian hyperspectral earth observation satellite. This Canadian hyperspectral remote sensing project is now named the Hyperspectral Environment and Resource Observer (HERO) Mission. In 2005, the Preliminary System Requirement Review (PSRR) and the Phase A (Preliminary Mission Definition) were concluded. Recent developments regarding the payload include an extensive comparison of potential optical designs. The payload uses separate grating spectrometers for the visible near-infrared and short-wave infrared portions of the spectrum. The instrument covers a swath of >30 km, has a ground sampling distance of 30 m, a spectral range of 400-2500 nm, and a spectral sampling interval of 10 nm. Smile and keystone are minimized. Recent developments regarding the mission include requirements simplification, data compression studies, and hyperspectral data simulation capability. In addition, a Prototype Data Processing Chain (PDPC) has been defined for 3 key hyperspectral applications. These are: geological mapping in the arctic environment, dominant species identification for forestry, and leaf area index for estimating foliage cover as well as forecasting crop growth and yield in agriculture.

A simplified second-order HMM with application to face recognition

In this paper, we propose a novel approach to simplify the second-order 2-D HMM as applied to the problem of Face Recognition (FR). The proposed approach exploits the nonoverlapped feature block conditions and the independence that arises in the conditional statistical relationship between feature blocks in close neighborhoods. System performance is studied and the impact of the number of states and the kernels of the state probability density function is highlighted. The system was tested on the facial database of AT&T Laboratories Cambridge [1] and a recognition rate up to 100% has been achieved with relatively low complexity.

Adaptive environment classification system for hearing aids

An adaptive sound classification framework is proposed for hearing aid applications. The long-term goal is to develop fully trainable instruments in which both the acoustical environments encountered in daily life and the hearing aid settings preferred by the user in each environmental class could be learned. Two adaptive classifiers are described, one based on minimum distance clustering and one on Bayesian classification. Through unsupervised learning, the adaptive systems allow classes to split or merge based on changes in the ongoing acoustical environments. Performance was evaluated using real-world sounds from a wide range of acoustical environments. The systems were first initialized using two classes, speech and noise, followed by a testing period when a third class, music, was introduced. Both systems were successful in detecting the presence of an additional class and estimating its underlying parameters, reaching a testing accuracy close to the target rates obtained from best-case scenarios derived from non-adaptive supervised versions of the classifiers (about 3% lower performance). The adaptive Bayesian classifier resulted in a 4% higher overall accuracy upon splitting adaptation than the minimum distance classifier. Merging accuracy was found to be the same in the two systems and within 1%-2% of the best-case supervised versions.

A semi-continuous state transition probability HMM-based voice activity detection

In this paper, we introduce an efficient hidden Markov model-based voice activity detection (VAD) algorithm with time-variant state transition probabilities in the underlying Markov chain. The transition probabilities vary in an exponential charge/discharge scheme and are softly merged with state conditional likelihood into a final VAD decision. Working in the domain of ITU-T G.729 parameters, with no additional cost for feature extraction, the proposed algorithm significantly outperforms G.729 Annex B VAD while providing a balanced tradeoff between clipping and false detection errors. The performance compares very favorably with adaptive multirate VAD, phase 2 (AMR2).

Hybrid hidden Markov model for face recognition

In this paper, we introduce a hybrid hidden Markov model (HMM) face recognition system. The proposed system contains a low-complexity 2D HMM-based face recognition (LC 2D-HMM FR) module that carries out a complete search in the compressed domain followed by a 1D HMM-based face recognition (1D-HMM FR) module which refines the search based on a candidate list provided by the first module. We also examine a remote database search methodology that may be helpful for accessing remote resources, where no prior information is assumed regarding the contents of the remote database. The performance of the hybrid HMM face recognition system is reported for both local and remote database search modes.

A tied-mixture 2D HMM face recognition system

In this paper, a simplified 2D second-order hidden Markov model (HMM) with tied state mixtures is applied to the face recognition problem. The mixture of the model states is fully-tied across all models for lower complexity. Tying HMM parameters is a well-known solution for the problem of insufficient training data leading to nonrobust estimation. We show that parameter tying in HMM also enhances the resolution in the case of small model. The performance of the proposed 2D HMM tied-mixture system is studied for the face recognition problem and the expected improved robustness is confirmed.

A semi-continuous state-transition probability HMM-based voice activity detector

We introduce an efficient hidden Markov model-based voice activity detection (VAD) algorithm with time-variant state-transition probabilities in the underlying Markov chain. The transition probabilities vary in an exponential charge/discharge scheme and are softly merged with state conditional likelihood into a final VAD decision. Working in the domain of ITU-T G.729 parameters, with no additional cost for feature extraction, the proposed algorithm significantly outperforms G.729 Annex B VAD while providing a balanced tradeoff between clipping and false detection errors. The performance compares very favorably with the adaptive multirate VAD, option 2 (AMR2).

Spectral angle mapper based assessment of detectability of man-made targets from hyperspectral imagery after SNR enhancement

This paper assesses the effectiveness of a signal-to-noise ratio (SNR) enhancement technology for hyperspectral imagery to examine whether it can better serve remote sensing applications. A hyperspectral data set acquired using an airborne Short-wave-infrared Full Spectrum Image II with man-made targets in the scene of the data set was tested. Spectral angle mapper and end-members of different target materials were used to measure the superficies of the targets and to assess the detectability of the targets before and after applying the SNR enhancement technology to the data set. The experimental results show that small targets, which cannot be detected in the original data set due to inadequate SNR and low spatial resolution, can be detected after the SNR of the data set is enhanced.