Ahmed Aldhahab

Employing vector quantization in a transform domain for face recognition

A face recognition system using an integration of Discrete Cosine Transform (DCT) and Vector quantization (VQ) is proposed in this paper. The system consists of two main phases, namely, Feature Extraction and Recognition. In the first phase, the input facial image is divided into blocks with dimensions equal to the codeword dimensions. Then, DCT is applied on each block. The codebook is initialized using the Kekre Fast Codebook Generation (KFCG) method. The Final Codebook computed using VQ algorithm efficiently represents the input facial image. The second phase aims to find the recognition rates based on the Euclidean distance criterion. The system is evaluated using four different databases, namely, ORL, YALE, FERET, and FEI that have different facial variations, such as facial expressions, illuminations, etc. The experimental results are analyzed using K-fold Cross Validation (CV). The proposed system is shown to improve the storage requirements, as well as the recognition rates.

High Performance and Efficient Facial Recognition Using Norm of ICA/Multiwavelet Features

In this paper, a supervised facial recognition system is proposed. For feature extraction, a Two-Dimensional Discrete Multiwavelet Transform (2D DMWT) is applied to the training databases to compress the data and extract useful information from the face images. Then, a Two-Dimensional Fast Independent Component Analysis (2D FastICA) is applied to different combinations of poses corresponding to the subimages of the low-low frequency subband of the MWT, and the \(\ell _2\)-norm of the resulting features are computed to obtain discriminating and independent features, while achieving significant dimensionality reduction. The compact features are fed to a Neural Network (NNT) based classifier to identify the unknown images. The proposed techniques are evaluated using three different databases, namely, ORL, YALE, and FERET. The recognition rates are measured using K-fold Cross Validation. The proposed approach is shown to yield significant improvement in storage requirements, computational complexity, as well as recognition rates over existing approaches.

Face Recognition Employing DMWT Followed by FastICA

Face recognition becomes a challenging topic in several fields since images of faces are varied by changing illuminations, facial rotations, facial expressions, etc. In this paper, two dimensional discrete multiwavelet transform (2D DMWT) and fast independent component analysis (FastICA) are proposed for face recognition. Preprocessing, feature extraction, and classification are the main steps in the proposed system. In the preprocessing step, each pose in the database is divided into six parts to reduce the effect of unnecessary facial features and highlight the local features in each part. For feature extraction, the 2D DMWT is applied to each part for dimensionality reduction and features extraction. This results in two facial representations. Then FastICA followed by

Supervised facial recognition based on eigenanalysis of multiresolution and independent features

\ell _2

Supervised facial recognition based on multiresolution analysis with radon transform

ℓ2-norm is applied to each representation, which produces six and three different techniques for the first and second representation, respectively. This results in features that are more discriminating, less dependent, and more compressed. In the recognition step, the resulted compressed features from the two representations are fed to a neural network-based classifier for training and testing. The proposed techniques are extensively evaluated using five databases, namely ORL, YALE, FERET, FEI, and LFW, which have different facial variations, such as illuminations, rotations, facial expressions, etc. The results are analyzed using K-fold cross-validation. Sample results and comparison with a large number of recently proposed approaches are provided. The proposed approach is shown to yield significant improvement compared with the other approaches.

A facial recognition method based on DMW transformed partitioned images

A supervised facial recognition system is proposed in this paper. There are three main phases in the proposed system, namely, Preprocessing, Feature Extraction, and Classification. Cropping, choosing appropriate dimensions, and prefiltering are performed in the first phase. In the feature extraction phase, Two Dimensional Discrete Multiwavelet Transform (2D DMWT) is applied to the facial images to compact the data and extract useful information. Then, Two Dimensional Fast Independent Component Analysis (2D FastICA) is applied to the extracted features to obtain efficient features with enhanced discriminating and independent properties. Finally, the efficient features are compressed in one single column by applying ℓ2-Norm. Then, the computed ℓ2-Norm features are fed into a Neural Network (NN) classifier, which employs Back Propagation Training Algorithm (BPTA) for the recognition task. The proposed techniques are evaluated using four different databases, namely, ORL, YALE, FERET, and FEI that have different facial expressions, light conditions, rotations, etc. The results of the proposed system are analyzed by using K-fold Cross Validation (CV). The experimental results of the proposed techniques are shown to improve the recognition rates, computational complexity, as well as the storage requirements compared to the some of the existing approaches.

Employing vector quantization algorithm in a transform domain for facial recognition

In this paper, a supervised facial recognition system is presented. In the feature extraction step, a Two Dimensional Discrete Multiwavelet Transform (2D DMWT) is used to extract useful information from the face images. The 2D DMWT is followed by a Two-Dimensional Fast Independent Component Analysis (2D FastICA) and eigendecomposition to obtain discriminating and independent features. The resulting compressed features are fed into a Neural Network (NNT) based classifier for training and testing. All techniques are tested using ORL, YALE, and FERET databases. The proposed approach shows a significant improvement in the recognition rate, storage requirements, as well as computational complexity.

Employing vector quantization on detected facial parts for face recognition

A new supervised algorithm for face recognition based on the integration of Two-Dimensional Discrete Multiwavelet Transform (2-D DMWT), 2-D Radon Transform, and 2-D Discrete Wavelet Transform (2-D DWT) is proposed1. In the feature extraction step, Multiwavelet filter banks are used to extract useful information from the face images. The extracted information is then aligned using the Radon Transform, and localized into a single band using 2-D DWT for efficient sparse data representation. This information is fed into a Neural Network based classifier for training and testing. The proposed method is tested on three different databases, namely, ORL, YALE and subset fc of FERET, which comprise different poses and lighting conditions. It is shown that this approach can significantly improve the classification performance and the storage requirements of the overall recognition system.