Mustafa Mumtaz

Wavelet based palmprint authentication system

Palmprint based personal verification has quickly entered the biometric family due to its ease of acquisition, high user acceptance and reliability. This paper proposes a palm print based identification system using the textural information, employing different wavelet transforms. The transforms employed have been analyzed for their individual as well as combined performances at feature level. The wavelets used for the analysis are Biorthogonal, Symlet and Discrete Meyer. The analysis of these wavelets is carried out on 500 images, acquired through indigenously made image acquisition system. 500 palmprint obtained from 50 users with 10 samples each have been collected over a period of six months and have been evaluated for the performance of the proposed system. The experimental results obtained from the data have demonstrated the feasibility of the proposed system by exhibiting Genuine Acceptance Rate, GAR of 97.12%.

A feature level multimodal approach for palmprint identification using directional subband energies

Palmprint based personal identification has gained preference over other biometric modalities due to its ease of acquisition, high user acceptance and reliability. This paper presents a palmprint based identification approach which uses the textural information available on the palmprint by employing a feature level fusion of contourlet transform (CT) and non-subsampled contourlet transform (NSCT). The proposed algorithm captures both local and global details in a palmprint as a compact fixed length palm code. After establishing the region of interest (ROI), the two-dimensional (2-D) spectrum is divided into fine slices using iterated directional filterbanks. Next, directional energy component for each block from the decomposed subband outputs is computed separately for the two transforms. The features from both domains are then fused at feature levels. Palmprint matching is then performed using normalized Euclidean distance classifier. The algorithm is tested on complete database of 7752 palm images of Polytechnic University of Hong Kong, and 500 palm images of GPDS Hand database from University of Las Palmas de Gran Canaria. The experimental results were compiled for features based upon individual transforms and fused one. CT based approach demonstrated the decidability index of 2.7734 and equal error rate (EER) of 0.2333% while NSCT based approach depicted decidability index of 2.8125 and EER of 0.1604% on palm database of Polytechnic University of Hong Kong. Similarly, CT based approach demonstrated the decidability index of 2.6212 and equal error rate (EER) of 0.7082% while NSCT based approach depicted decidability index of 2.7278 and EER of 0.5082% on GPDS hand database. The multimodal approach based upon feature fusion achieved decidability index of 2.8914 and EER of 0.1563% on database of Polytechnic University of Hong Kong and decidability index of 2.7956 and EER of 0.3112% on GPDS hand database. The quantitative measures confirm progressive improved results in three approaches for both the databases.

Combined Contourlet and Non-subsampled Contourlet Transforms Based Approach for Personal Identification Using Palmprint

Palmprint based personal verification is an accepted biometric modality due to its reliability, ease of acquisition and user acceptance. This paper presents a novel palmprint based identification approach which draw on the textural information available on the palmprint by utilizing a combination of Contourlet and Non Subsampled Contourlet Transforms. Center of the palm is computed using the Distance Transform whereas the parameters of best fitting ellipse help determine the alignment of the palmprint. ROI of 256X256 pixels is cropped around the center, and subsequently it is divided into fine slices, using iterated directional filterbanks. Next, directional energy components for each block of the decomposed subband outputs are computed using Contourlet and Non Subsampled Contourlet Transforms. The proposed algorithm captures global details in a palmprint as compact fixed length palm codes for Contourlet and NSCT respectively which are further concatenated at feature level for identification using normalized Euclidean distance classifier. The proposed algorithm is tested on a total of 500 palm images of GPDS Hand database, acquired from University of Las Palmas de Gran Canaria. The experimental results were compiled for individual transforms as well as for their optimized combination at feature level. CT based approach demonstrated the Decidability Index of 2.6212 and Equal Error Rate (EER) of 0.7082% while NSCT based approach depicted Decidability Index of 2.7278 and EER of 0.5082%. The feature level fusion achieved Decidability Index of 2.7956 and EER of 0.3112%.

Palmprint Identification Using Contourlet Transform

Palmprint based personal verification has gained preference over other biometric modalities due to its ease of acquisition, high user acceptance and reliability. This paper presents a novel palmprint based identification approach which uses the textural information available on the palmprint by employing the Contourlet Transform (CT). After establishing the region of interest (ROI), the two dimensional (2-D) spectrums is divided into fine slices, using iterated directional filterbanks. Next, directional energy component for each block from the decomposed subband outputs is computed. The proposed algorithm captures both local and global details in a palmprint as a compact fixed length palm code. Palmprint matching is then performed using normalized Euclidean distance classifier. The proposed algorithm is tested on a total of 7752 palm images, acquired from the standard database of Polytechnic University of Hong Kong. The experimental results demonstrated the feasibility of the proposed system by exhibiting genuine acceptance rate of 88.91%, decidability index of 2.7748 and equal ierror rate of 0.2333%.

Personal identification using feature and score level fusion of palm- and fingerprints

The ever increasing demand of security has resulted in wide use of Biometric systems. Despite overcoming the traditional verification problems, the unimodal systems suffer from various challenges like intra class variation, noise in the sensor data etc, affecting the system performance. These problems are effectively handled by multimodal systems. In this paper, we present multimodal approach for palm- and fingerprints by feature level and score level fusions (sum and product rules). The proposed multi-modal systems are tested on a developed database consisting of 440 palm- and fingerprints each of 55 individuals. In feature level fusion, directional energy-based feature vectors of palm- and fingerprint identifiers are combined to form joint feature vector that is subsequently used to identify the individual using a distance classifier. In score level fusion, the matching scores of individual classifiers are fused by sum and product rules. Receiver operating characteristics curves are formed for unimodal and multimodal systems. Equal Error Rate (EER) of 0.538% for feature level fusion shows best performance compared to score level fusion of 0.6141 and 0.5482% of sum and product rules, respectively. Multimodal systems, however, significantly outperform unimodal palm- and fingerprints identifiers with EER of 2.822 and 2.553%, respectively.

Directional energy based palmprint identification using Non Subsampled Contourlet Transform

Palmprint based personal verification has gained preference over other biometric modalities due to its ease of acquisition, high user acceptance and reliability. This paper presents a novel palmprint based identification approach which uses the textural information available on the palmprint by employing the Non Subsampled Contourlet Transform (NSCT). After establishing the region of interest (ROI), the two dimensional (2-D) spectrum is divided into fine slices, using iterated directional filterbanks. Next, directional energy component for each block from the decomposed subband outputs is computed. The proposed algorithm captures both local and global details in a palmprint as a compact fixed length palm code. Palmprint matching is then performed using Normalized Euclidean Distance classifier. The algorithm is tested on a total of 7752 palm images, acquired from the standard database of Polytechnic University of Hong Kong. The experimental results demonstrated the feasibility of the proposed system by exhibiting Decidability Index of 2.8125 and Equal Error Rate of 0.1604%, better than the reported techniques in literature.

A New Approach to Aircraft Surface Inspection Based on Directional Energies of Texture

Non Destructive Inspections (NDI) plays a vital role in aircraft industry as it determines the structural integrity of aircraft surface and material characterization. The existing NDI methods are time consuming, we propose a new NDI approach using Digital Image Processing that has the potential to substantially decrease the inspection time. The aircraft imagery is analyzed by two methods i.e Contourlet Transform (CT) and Discrete Cosine Transform (DCT). With the help of Contourlet Transform the two dimensional (2-D) spectrum is divided into fine slices, using iterated directional filter banks. Next, directional energy components for each block of the decomposed subband outputs are computed. These energy values are used to distinguish between the crack and scratch images using the Dot Product classifier. In next approach, the aircraft imagery is decomposed into high and low frequency components using DCT and the first order moment is determined to form feature vectors. A correlation based approach is then used for distinction between crack and scratch surfaces. A comparative examination between the two techniques on a database of crack and scratch images revealed that texture analysis using the combined transform based approach gave the best results by giving an accuracy of 96.6% for the identification of crack surfaces and 98.3% for scratch surfaces.

Directional Energy Based Feature Level Multimodal System Using Palm and Fingerprints

The ever increasing demand of security has resulted in wide use of Biometric systems. Despite overcoming the traditional verification problems, the unimodal systems suffer from various challenges like intra class variation, noise in the sensor data etc, affecting the system performance. These problems are effectively handled by multimodal systems. In this paper, we present a feature level fused multimodal approach using palm and finger prints. Directional energy based feature vectors of palm and fingerprint identifiers are combined to form joint feature vector that is subsequently used to identify the individual using a distance classifier. The proposed multimodal system is tested on a developed database consisting of 440 palm and finger prints each of 55 individuals. Receiver Operating Characteristics curves are formed for unimodal and multimodal systems. Equal Error Rate (EER) of 0.538% for multimodal system depicts improved performance compared to 2.822% and 2.553% of palm and finger prints identifiers respectively.

Automatic detection of retinal hemorrhages by exploiting image processing techniques for screening retinal diseases in diabetic patients

Diabetic retinopathy (DR) is one of the main retinal abnormalities which is asymptomatic and is the main cause of vision loss in diabetic patients. The computer-aided diagnosis systems based on image processing not only facilitate the doctor but also decrease the diagnosis time. This work represents the automated detection of one of the red lesion, i.e., hemorrhages, which are one of the most distinctive signs of retinal diseases in diabetic patients. In the proposed method, the foremost step is to enhance the image quality by eliminating the background noise and nonuniform illumination. This is achieved by applying the methods such as image contrast enhancement and normalization. The subsequent step is to segment the blood vessels from hemorrhages (using scale-based method) as both of them have the same color. The last step is to delineate the hemorrhages by exploiting the gamma correction and global thresholding techniques. The proposed method has achieved specificity (SP) of 84%, sensitivity (SN) of 87%, and an accuracy of 89 % on the DIARETDB1 database.

Image-based spacecraft pointing model using single-bank dual-band registration

The growing interest in the development of small satellites and the demand for high-resolution imaging has made the pointing and drift rate requirements of a satellite more stringent. To achieve high pointing accuracy, star sensors can be used, but their size and weight are too large for small satellites. The need for keeping the overall cost of the spacecraft down and still achieve adequate pointing accuracies has provoked the development of relatively inexpensive and high-performance attitude systems that can provide competitive pointing accuracies during imaging operations. In order to realize such a system, this research describes a novel approach for finding the attitude of a satellite at any arbitrary rotation by using inter-band offsets from a single multi-spectral imager (MSI). For Earth observational imagery, UK Disaster Monitoring Constellation Earth-pointing MSI is used. This research focuses on the potential use of a narrow angle between the bands of a pushbroom sensor for determining the attitude of a spacecraft. The technique investigated does not require ground control points or knowledge of any ground features, but rather estimates the orientation of the platform through analysis of perspective and timing-based distortions between images. These distortions are assumed translational and affine in nature, with two-dimensional shifts being extracted from imagery using a Singular Value Decomposition-based registration scheme. In order to better understand the effect of attitude on imagery, a model was developed for predicting inter-band shifts given an attitude. This was then used to estimate the shifts between imagery at nominal attitude and given a series of simulated manoeuvres. Several simulations have shown that the row and column offsets represented a straight line. Hence, we expressed the row and column shifts in terms of straight line parameters. These geometric attributes are then represented in terms of Euler axis/angle to find the mapping for the elements of the general rotation matrix. Once the mapping is computed for the elements of the rotation matrix, we used the standard equations to determine the angle of rotation and Euler axis. The accuracy of attitude estimates depends on the magnitude of angular separation between the cameras, orientation of spacecraft, sensor resolution, image texture, and image registration method. The technique proposed in this study may however be applied to any satellite with pushbroom sensors that have a discernable along track separation and sufficient overlap.