Noor Almaadeed

Speaker identification using multimodal neural networks and wavelet analysis

The rapid momentum of the technology progress in the recent years has led to a tremendous rise in the use of biometric authentication systems. The objective of this research is to investigate the problem of identifying a speaker from its voice regardless of the content. In this study, the authors designed and implemented a novel text-independent multimodal speaker identification system based on wavelet analysis and neural networks. Wavelet analysis comprises discrete wavelet transform, wavelet packet transform, wavelet sub-band coding and Mel-frequency cepstral coefficients (MFCCs). The learning module comprises general regressive, probabilistic and radial basis function neural networks, forming decisions through a majority voting scheme. The system was found to be competitive and it improved the identification rate by 15% as compared with the classical MFCC. In addition, it reduced the identification time by 40% as compared with the back-propagation neural network, Gaussian mixture model and principal component analysis. Performance tests conducted using the GRID database corpora have shown that this approach has faster identification time and greater accuracy compared with traditional approaches, and it is applicable to real-time, text-independent speaker identification systems.

Emotion recognition from scrambled facial images via many graph embedding

Proposed a novel dimensionality reduction method based on many manifold hypothesis.Developed a successful scheme for facial expression verification in the scrambled domain.Successfully validate the proposed scheme in experiments.Successfully tackled with the challenges of chaotic pattern analysis. Facial expression verification has been extensively exploited due to its wide application in affective computing, robotic vision, man-machine interaction and medical diagnosis. With the recent development of Internet-of-Things (IoT), there is a need of mobile-targeted facial expression verification, where face scrambling has been proposed for privacy protection during image/video distribution over public network. Consequently, facial expression verification needs to be carried out in a scrambled domain, bringing out new challenges in facial expression recognition. An immediate impact from face scrambling is that conventional semantic facial components become not identifiable, and 3D face models cannot be clearly fitted to a scrambled image. Hence, the classical facial action coding system cannot be applied to facial expression recognition in the scrambled domain. To cope with chaotic signals from face scrambling, this paper proposes an new approach Many Graph Embedding (MGE) to discover discriminative patterns from the subspaces of chaotic patterns, where the facial expression recognition is carried out as a fuzzy combination from many graph embedding. In our experiments, the proposed MGE was evaluated on three scrambled facial expression datasets: JAFFE, MUG and CK++. The benchmark results demonstrated that the proposed method is able to improve the recognition accuracy, making our method a promising candidate for the scrambled facial expression recognition in the emerging privacy-protected IoT applications.

Robust model-free gait recognition by statistical dependency feature selection and Globality-Locality Preserving Projections

Gait recognition aims to identify people through the analysis of the way they walk. The challenge of model-free based gait recognition is to cope with various intra-class variations such as clothing variations and carrying conditions that adversely affect the recognition performances. This paper proposes a novel method which combines Statistical Dependency (SD) feature selection with Globality-Locality Preserving Projections (GLPP) to alleviate the impact of intra-class variations so as to improve the recognition performances. The proposed method has been evaluated using CASIA Gait database (Dataset B) under variations of clothing and carrying conditions. The experimental results demonstrate that the proposed method achieves a Correct Classification Rate (CCR) up to 86% when compared to existing state-of-the-art methods.

Audio-Visual feature fusion for speaker identification

Analyses of facial and audio features have been considered separately in conventional speaker identification systems. Herein, we propose a robust algorithm for text-independent speaker identification based on a decision-level and feature-level fusion of facial and audio features. The suggested approach makes use of Mel-frequency Cepstral Coefficients (MFCCs) for audio signal processing, Viola-Jones Haar cascade algorithm for face detection from video, eigenface features (EFF) and Gaussian Mixture Models (GMMs) for feature-level and decision-level fusion of audio and video. Decision-level fusion is carried out using PCA for face and GMM for audio through AND voting. Feature-level fusion is investigated by combining both MFCC (audio) and PCA (face) features to construct a hybrid GMM for each speaker. Testing on GRID, a multi-speaker audio-visual database, shows that the decision-level fusion of PCA (face) and GMM (audio) achieves 98.2 % accuracy and it is almost 15 % more efficient than feature-level fusion.

Indoor visible light communication localization system utilizing received signal strength indication technique and trilateration method

Abstract. Visible light communication (VLC) based on light-emitting diodes (LEDs) technology not only provides higher data rate for indoor wireless communications and offering room illumination but also has the potential for indoor localization. VLC-based indoor positioning using the received optical power levels from emitting LEDs is investigated. We consider both scenarios of line-of-sight (LOS) and LOS with non-LOS (LOSNLOS) positioning. The performance of the proposed system is evaluated under both noisy and noiseless channel as is the impact of different location codes on positioning error. The analytical model of the system with noise and the corresponding numerical evaluation for a range of signal-to-noise ratio (SNR) are presented. The results show that an accuracy of <10  cm on average is achievable at an SNR>12  dB.

Robust gait recognition: a comprehensive survey

Gait recognition has emerged as an attractive biometric technology for the identification of people by analysing the way they walk. However, one of the main challenges of the technology is to address the effects of inherent various intra-class variations caused by covariate factors such as clothing, carrying conditions, and view angle that adversely affect the recognition performance. The main aim of this survey is to provide a comprehensive overview of existing robust gait recognition methods. This is intended to provide researchers with state of the art approaches in order to help advance the research topic through an understanding of basic taxonomies, comparisons, and summaries of the state-of-the-art performances on several widely used gait recognition datasets.

Random sampling for patch-based face recognition

Real face recognition is a challenging problem especially when face images are subject to distortions. This paper presents an approach to tackle partial occlusion distortions present in real face recognition using a single training sample per person. First, original images are partitioned into multiple blocks and Local Binary Patterns are applied as a local descriptor on each block separately. Then, a dimensionality reduction of the resulting descriptors is carried out using Kernel Principle Component Analysis. Once done, a random sampling method is used to select patches at random and hence build several sub-SVM classifiers. Finally, the results from each sub-classifier are combined in order to increase the recognition performance. To demonstrate the usefulness of the approach, experiments were carried on the AR Face Database and obtained results have shown the effectiveness of our technique.

Multispectral palmprint recognition based on local binary pattern histogram fourier features and gabor filter

Fusing multiple features within one biometric modality has attracted increasing attention and interest among researchers during recent decades because the concept is useful in addressing a wide range of real world problems. In this paper, we propose a novel fusion approach that combines two feature extraction algorithms: Local Binary Pattern Histogram Fourier Features (LBP-HF) and Gabor filter technique for use as one feature extraction. The fused features are applied to improve the performance of palmprint recognition. However, the main problem associated with this approach is the extremely large number of features, which can result in an overfitting problem for classification. To overcome this difficulty, spectral regression kernel discriminant analysis (SR-KDA) is applied as a dimensionality reduction technique. When designing the proposed recognition system, the k-nearest neighbour (KNN) classifier is used for the final decision. The performance of the proposed approach was evaluated using the challenging multispectral palmprint PolyU database. From the experimental results, it can be suggested that the system presented consistently yields significant performance gains compared to the state-of-the art methods.