Export 7 results:
Sort by: Author Title Type [ Year  (Desc)]
Melek, M., A. Khattab, and M. F. Abu-ElYazeed, "Fast matching pursuit for sparse representation-based face recognition", IET Image Processing, vol. 12, issue 10, pp. 1807-1814, 2018. Abstract

Even though face recognition is one of the most studied pattern recognition problems, most existing solutions still lack efficiency and high speed. Here, the authors present a new framework for face recognition which is efficient, fast, and robust against variations of illumination, expression, and pose. For feature extraction, the authors propose extracting Gabor features in order to be resilient to variations in illumination, facial expressions, and pose. In contrast to the related literature, the authors then apply supervised locality-preserving projections (SLPP) with heat kernel weights. The authors’ feature extraction approach achieves a higher recognition rate compared to both traditional unsupervised LPP and SLPP with constant weights. For classification, the authors use the recently proposed sparse representation-based classification (SRC). However, instead of performing SRC using the computationally expensive ℓ1 minimisation, the authors propose performing SRC using fast matching pursuit, which considerably improves the classification performance. The authors’ proposed framework achieves ∼99% recognition rate using four benchmark face databases, significantly faster than related frameworks.

Abdel-Sayed, M. M., A. Khattab, and M. F. Abu-Elyazeed, "Wideband compressed sensing using Wavelet Packet Adaptive Reduced-set Matching Pursuit", 2018 International Conference on Innovative Trends in Computer Engineering (ITCE), Aswan, Egypt, 2018. Abstract

One of the unsolved challenges in cognitive radio networks (CRNs) is the inability to sense a wideband spectrum in real-time. Traditional techniques require the use of analog-to-digital converters (ADCs) of very high sampling rate, given by the Nyquist theorem. Recently, compressed sensing has presented itself as an efficient solution for spectrum sensing aiming to reduce such requirement. However, the complexity and speed of traditional compressed sensing recovery algorithms not particularly developed for CRNs prevented such an application. In this paper, we present the Wavelet Packet Adaptive Reduced-set Matching Pursuit (WP-ARMP) approach for compressed wideband spectrum sensing. WP-ARMP is a fast and accurate greedy recovery algorithm for compressed sensing, which is suitable for real-time CRN applications. Furthermore, we exploit the sparsity of the spectrum in the wavelet packet domain. Simulation results show that our technique can reconstruct spectrum signals from samples collected at 1/4 the Nyquist sampling rate. The proposed scheme is not only much faster than other related techniques, but also results in over 99% probability of detection and a probability of false alarm below 1%.

Abdel-Sayed, M. M., A. Khattab, and M. F. Abu-ElYazeed, "Fast matching pursuit for wideband spectrum sensing in cognitive radio networks", Wireless Networks, Jun, 2017. AbstractWebsite

Wideband spectrum sensing is one of the most challenging components of cognitive radio networks. It should be performed as fast and accurately as possible. Traditional wideband spectrum sensing techniques suffer from the requirement of analog-to-digital converters with very high sampling rates. Compressed sensing has been recently considered as a technique that may enable wideband spectrum sensing at a much lower sampling rate than that dictated by the Nyquist theorem. However, the complexity and speed of existing compressed sensing reconstruction techniques remained a barrier for such an application. In this paper, we introduce fast matching pursuit (FMP), a fast and accurate greedy recovery algorithm for compressed sensing. We show that the spectral data are sparse in the Haar wavelet and wavelet packet domains. We apply FMP to wideband spectrum sensing for cognitive radio networks. Our proposed algorithm is capable of reconstructing spectrum signals from samples at a rate of about 25{%} of the Nyquist rate, significantly faster than other related algorithms, at more than 99{%} probability of detection and less than 1{%} probability of false alarm.

Abdel-Sayed, M. M., A. Khattab, and M. F. Abu-Elyazeed, "Sparse representation classification via fast matching pursuit for face recognition", 2017 Japan-Africa Conference on Electronics, Communications and Computers (JAC-ECC), Alexandria, Egypt, 2017. Abstract

Face recognition is a widely studied pattern recognition problem. One of the most crucial components of face recognition problems is classification. Sparse representation-based classification (SRC) has been recently proposed to considerably improve the classification performance by using the compressed sensing theory. However, SRC utilizes ℓ1minimization for recovery. Despite being optimal, ℓ1minimization is computationally expensive, and hence, not applicable in real-time applications. In this paper, we present the Fast Matching Pursuit (FMP) which is a compressed sensing recovery algorithm that results in a recognition time that is only 4% to 10% of that of ℓ1minimization and approximately half the time of existing related matching pursuit approaches. This significant speedup does not come at the expense of any degradation in the recognition rate.

Abdel-Sayed, M. M., A. Khattab, and M. F. Abu-Elyazeed, "Application of Compressed Sensing to Wideband Spectrum Sensing in Cognitive Radio Networks", International Conference on Acoustics, Speech and Signal Processing (ICASSP), New Orleans, LA, IEEE, 2017. Abstract
Abdel-Sayed, M., A. Khattab, and M. Abu-Elyazeed, "Adaptive Reduced-Set Matching Pursuit for Compressed Sensing Recovery", International Conference on Image Processing (ICIP), Phoenix, Arizona, IEEE, 2016. Abstract
Abdel-Sayed, M. M., A. Khattab, and M. F. Abu-Elyazeed, "RMP: Reduced-set Matching Pursuit Approach for Efficient Compressed Sensing Signal Reconstruction", Journal of Advanced Research, vol. 7, pp. 851–861, 2016. Abstract