Rohayanti Hassan

Multimodal biometrics: Weighted score level fusion based on non-ideal iris and face images

The iris and face are among the most promising biometric traits that can accurately identify a person because their unique textures can be swiftly extracted during the recognition process. However, unimodal biometrics have limited usage since no single biometric is sufficiently robust and accurate in real-world applications. Iris and face biometric authentication often deals with non-ideal scenarios such as off-angles, reflections, expression changes, variations in posing, or blurred images. These limitations imposed by unimodal biometrics can be overcome by incorporating multimodal biometrics. Therefore, this paper presents a method that combines face and iris biometric traits with the weighted score level fusion technique to flexibly fuse the matching scores from these two modalities based on their weight availability. The dataset use for the experiment is self established dataset named Universiti Teknologi Malaysia Iris and Face Multimodal Datasets (UTMIFM), UBIRIS version 2.0 (UBIRIS v.2) and ORL face databases. The proposed framework achieve high accuracy, and had a high decidability index which significantly separate the distance between intra and inter distance.

Feature extraction for different distances of visible reflection iris using multiscale sparse representation of local Radon transform

Iris recognition is a promising method by which to accurately identify a person. During the iris recognition stage, the features of the iris are extracted, including the unique, individual texture of the iris. The ability to extract the texture of the iris in non-cooperative environments from eye images captured at different distances, containing reflections, and under visible wavelength illumination will lead to increased iris recognition performance. A method that combined multiscale sparse representation of local Radon transform was proposed to down sample a normalized iris into different lengths of scales and different orientations of angles to form an iris feature vector. This research was tested using 1000 eye images from the UBIRIS.v2 database. The results showed that the proposed method performed better than existing methods when dealing with iris images captured at different distances.

A low lighting or contrast ratio visible iris recognition using iso-contrast limited adaptive histogram equalization

Condition of eye images with a low lighting or low contrast ratio between the iris and pupil is one of the challenges for iris recognition in a non-cooperative environment and under visible wavelength illumination. Incorrect iris localization can affect the performance of the iris recognition system. Iso-contrast limited adaptive histogram equalization is proposed to overcome this challenge and increase the performance of iris localization. The eye image is partitioned into the contextual sub-region; then, the proposed method transfers the pixel intensity by referring to a local intensity histogram and a newly suggested cumulative distribution function. This research was tested on 1000 eye images from the UBIRIS.v2 dataset. The results showed that the proposed method performed better than existing methods when dealing with a low lighting or low contrast ratio between the iris and pupil in the eye image.

An improved multiscale retinex algorithm for motion-blurred iris images to minimize the intra-individual variations

Motion-blurred iris image is caused by less user cooperation, poor quality cameras and environmental conditions when capturing image, thus contributing to a variety of iris patterns, which are due to the shadows and noises occurring in the image. The biggest challenge dealing with motion-blurred iris image is to analyze the exact pattern of the iris image. The combination of homomorphic filtering and multiscale retinex algorithms can cope with the illumination changes and shadow removal in order to produce enhanced iris pattern. Homomorphic filtering is applied to remove shadows on motion-blurred image. The processed image that is free of shadows is then applied with multiscale retinex algorithm to improve the contrast of the image. The enhanced iris pattern that is free of shadows is then evaluated using intensity histogram to validate the proposed method. The accuracy of the proposed method is 99.2% with minimum false rejection and false acceptance rate.

Utilizing shared interacting domain patterns and Gene Ontology information to improve protein-protein interaction prediction

Protein-protein interactions (PPIs) play a significant role in many crucial cellular operations such as metabolism, signaling and regulations. The computational methods for predicting PPIs have shown tremendous growth in recent years, but problem such as huge false positive rates has contributed to the lack of solid PPI information. We aimed at enhancing the overlap between computational predictions and experimental results in an effort to partially remove PPIs falsely predicted. The use of protein function predictor named PFP() that are based on shared interacting domain patterns is introduced in this study with the purpose of aiding the Gene Ontology Annotations (GOA). We used GOA and PFP() as agents in a filtering process to reduce false positive pairs in the computationally predicted PPI datasets. The functions predicted by PFP() were extracted from cross-species PPI data in order to assign novel functional annotations for the uncharacterized proteins and also as additional functions for those that are already characterized by the GO (Gene Ontology). The implementation of PFP() managed to increase the chances of finding matching function annotation for the first rule in the filtration process as much as 20%. To assess the capability of the proposed framework in filtering false PPIs, we applied it on the available S. cerevisiae PPIs and measured the performance in two aspects, the improvement made indicated as Signal-to-Noise Ratio (SNR) and the strength of improvement, respectively. The proposed filtering framework significantly achieved better performance than without it in both metrics.

Fusing the line intensity profile and support vector machine for removing reflections in frontal RGB color eye images

RGB eye image is prune to study reflections with large and different intensities.The fusion of line intensity profile and support vector machine is proposed.Line intensity profile is used for reflection identification.Support vector machine is used to classify between reflections and non-reflections.The proposed combination is able to decrease equal error rate of iris recognition. Iris recognition is a promising method for accurate identification of a person where the capability of iris segmentation determines its overall performance. Correct iris area has to be determined so that an individuals unique features can be extracted and compared during feature extraction and template matching processes. However, current methods fall short in correctly identifying and classifying reflections in an eye image. This has often led to errors in iris boundary localization and consequently increases the equal error rate in iris recognition. This study thus intends to propose a method that combines a line intensity profile and a support vector machine where the former identifies reflections in eye images, and the latter classifies reflections and non-reflections. The combined method was tested using 1000 eye images from the UBIRISv2 database. Results showed that the combined method provided almost 99.9% classification accuracy. Generally, it has less than 10.5% equal error rate and high decidability index in iris recognition.

A compact hybrid feature vector for an accurate secondary structure prediction

Amino acid propensity score is one of the earliest successful methods used in protein secondary structure prediction. However, the score performs poorly on small-sized datasets and low-identity protein sequences. Based on current in silico method, secondary structure can be predicted from local folds or local protein structure. In biology, the evolution of secondary structure produces local protein structure with different lengths. To precisely predict secondary structures, we propose a derivative feature vector, DPS that utilizes the optimal length of the local protein structure. DPS is the unification of amino acid propensity score and dihedral angle score. This new feature vector is further normalized to level the edges. Prediction is performed by support vector machines (SVM) over the DPS feature vectors with class labels generated by secondary structure assignment method (SSAM) and secondary structure prediction method (SSPM). All experiments are carried out on RS126 sequences. The results from this proposed method also highlight the overall accuracy of our method compared to other state-of-the-art methods. The performance of our method was acceptable specifically in dealing with low number and low identity sequences.

Incorporating multiple genomic features with the utilization of interacting domain patterns to improve the prediction of protein-protein interactions

Protein-protein interaction (PPI) networks play an outstanding role in the organization of life. Parallel to the growth of experimental techniques on determining PPIs, the emergence of computational methods has greatly accelerated the time needed for the identification of PPIs on a wide genomic scale. Although experimental approaches have limitations that can be complemented by the computational methods, the results from computational methods still suffer from high false positive rates which contribute to the lack of solid PPI information. Our study introduces the PPI-Filter; a computational framework aimed at improving PPI prediction results. It is a post-prediction process which involves filtration, using information based on three different genomic features; (i) gene ontology annotation (GOA), (ii) homologous interactions and (iii) protein families (PFAM) domain interactions. In the study, we incorporated a protein function prediction method, based on interacting domain patterns, the protein function predictor or PFP (), for the purpose of aiding the GOA. The goal is to improve the robustness of predicted PPI pairs by removing the false positive pairs and sustaining as much true positive pairs as possible, thus achieving a high confidence level of PPI datasets. The PPI-Filter has been proven to be applicable based on the satisfactory results obtained using signal-to-noise ratio (SNR) and strength measurements that were applied on different computational PPI prediction methods.

SPlitSSI-SVM: An algorithm to reduce the misleading and increase the strength of domain signal

Protein domains contain information about the prediction of protein structure, function, evolution and design since the protein sequence may contain several domains with different or the same copies of the protein domain. In this study, we proposed an algorithm named SplitSSI-SVM that works with the following steps. First, the training and testing datasets are generated to test the SplitSSI-SVM. Second, the protein sequence is split into subsequence based on order and disorder regions. The protein sequence that is more than 600 residues is split into subsequences to investigate the effectiveness of the protein domain prediction based on subsequence. Third, multiple sequence alignment is performed to predict the secondary structure using bidirectional recurrent neural networks (BRNN) where BRNN considers the interaction between amino acids. The information of about protein secondary structure is used to increase the protein domain boundaries signal. Lastly, support vector machines (SVM) are used to classify the protein domain into single-domain, two-domain and multiple-domain. The SplitSSI-SVM is developed to reduce misleading signal, lower protein domain signal caused by primary structure of protein sequence and to provide accurate classification of the protein domain. The performance of SplitSSI-SVM is evaluated using sensitivity and specificity on single-domain, two-domain and multiple-domain. The evaluation shows that the SplitSSI-SVM achieved better results compared with other protein domain predictors such as DOMpro, GlobPlot, Dompred-DPS, Mateo, Biozon, Armadillo, KemaDom, SBASE, HMMPfam and HMMSMART especially in two-domain and multiple-domain.

A unified approach for unconstrained off-angle iris recognition

Improving the performance of non-idealistic iris recognition has recently become one of the main focus in iris biometric research. In real-world iris image acquisitions, it is common and unavoidable to capture off-angle iris images. Such off-angle iris images are categorized as non-idealistic because they substantially degrade the performance of iris recognition. In this paper, we present a unified framework designed to improve off-angle iris recognition performance. We propose combination of least square ellipse fitting (LSEF) technique and the geometric calibration (GC) technique for the iris segmentation. For off-angle images, the improper location of iris and pupil interferes with the ability to effectively segment the inner boundary and outer boundary of the iris image. With the proposed techniques, inner and outer boundaries are fitted iteratively. For feature extraction, we propose a NeuWave Network (inspired by the Haar wavelet decomposition and neural network). The iris features are represented using the wavelet coefficients. Each different angle of the iris have its own significant coefficient and these coefficient, with a set of weights, then forms the iris template. The approach is evaluated based on recognition accuracy measured by the false rejection, false acceptance rate, and decidability index. We evaluate the algorithms with WVU-IBIDC datasets.