Kamlesh Tiwari

Designing palmprint based recognition system using local structure tensor and force field transformation for human identification

Abstract This paper presents an efficient palmprint based automatic recognition system. It uses local structure tensor to extract features from the palmprint. Each enhanced palmprint image has been divided into sub-images and features are obtained based on local properties within the sub-image. Force field transformation is used to emphasize the texture of the palmprint and the chosen dominant orientation pixels are used for feature extraction to reduce the effect of noise. Structure tensor values of the dominant orientation pixels within a sub-image are averaged to form the tensor matrix for the sub-image. Eigen decomposition of each tensor matrix is used to generate the feature matrix. Euclidean distance between feature matrices of two palmprints has been used to make the decision on matching. The system has been tested on three databases viz. IITK, CASIA and PolyU and achieved high accuracy. It has also been compared with two best known systems using PolyU database and it has performed better than these two systems.

An Efficient Palmprint Based Recognition System Using 1D-DCT Features

This paper makes use of one dimensional Discrete Cosine Transform (DCT) to design an efficient palmprint based recognition system. It extracts the palmprint from the hand images which are acquired using a flat bed scanner at low resolution. It uses new techniques to correct the non-uniform brightness of the palmprint and to extract features using difference of 1D-DCT coefficients of overlapping rectangular blocks of variable size and variable orientation. Features of two palmprints are matched using Hamming distance while nearest neighbor approach is used for classification. The system has been tested on three databases, viz. IITK, CASIA and PolyU databases and is found to be better than the well known palmprint systems.

Fusion of 4-slap fingerprint images with their qualities for human recognition

This paper presents an efficient multimodel bio-metric system based on 4 slap fingerprint images. The system utilizes 4 slap fingerprint scanner to simultaneously collect fingerprints of multiple fingers on a hand in one image. The acquired multi-finger images are first segmented to get individual fingers. Quality of each individual finger is estimated and its minutiae points are extracted. The minutiae points of each individual finger extracted from gallery 4 slap fingerprint image is compared with the corresponding individual finger of the query 4 slap fingerprint image to get matching score of that finger. Matching score between two 4 slap fingerprint images is obtained by fusing matching scores of various fingers along with their respective image quality and relative accuracies. Decision of matching has been taken based on the fused matching score. The system has been tested on two 4 slap fingerprint databases viz IITK-student and IITK-rural containing 1007 and 991 subjects respectively. Both databases are acquired in 2 sessions. The correct recognition rate obtained is 91.00% for IITK-rural database and 99.64% for IITK-student database. Respective EER values are 5.64% and 0.94%.

Palmprint based recognition system using local structure tensor and force field transformation

This paper presents an efficient palmprint based recognition system. In this system, the image is divided into disjoint sub-images. For each sub-image, the dominant orientation pixels based on the force field transformation are identified. Structure tensor values of these dominant orientation pixels of each sub-image are averaged to form tensor matrix for the sub-image. Eigen decomposition of each tensor matrix is used to generate the feature matrix which is used to take decision on matching. The system has been tested on IITK database. The experimental results reveal the accuracy of 100% for the database.

Multiple texture information fusion for finger-knuckle-print authentication system

Abstract This paper proposes a finger-knuckle-print based authentication system by fusing multiple texture features. It contains new algorithms for extracting region of interest (ROI) with the help of curvature Gabor filters, image quality parameters, ROI enhancement using gradient based ordinal relationships, and dissimilarity measure for matching. The proposed system has been tested on the largest publicly available finger-knuckle-print PolyU database consisting of 7920 finger-knuckle-print images obtained from 165 subjects in two sessions. It has shown good performance.

An efficient technique for automatic segmentation of fingerprint ROI from digital slap image

Abstract Slap fingerprint scanner can simultaneously acquire fingerprint of four fingers of a human hand in a single image. Subsequently, the image is required to be segmented to get fingerprints of individual fingers. The paper proposes a novel and efficient technique to extract individual fingerprints. It applies a divide and conquer strategy by using force field and heuristics. The technique has been tested on two slap image databases viz. IITK-4Slap-Rural and IITK-4Slap-Student and has achieved high segmentation accuracy.

Segmentation of Slap Fingerprint Images

This paper proposes a novel technique to segment fingerprints from 4-slap image. Black pixels of down scaled and binarized slap images are subjected to experience a mutual superposition attractive force which is inversely proportional to the square of distance. Pixels having high force are grouped based on their force angles, and adjacent connected groups are merged to form components. These components are used to identify hand and to label fingers. The technique have been tested on IITK-Rural and IITK-Student databases and has achieved high segmentation accuracy of 96.80% and 99.2% respectively.

Indexing fingerprint database with minutiae based coaxial Gaussian track code and quantized lookup table

Large scale adaptation of a fingerprint based recognition system results in expansion of its database which increases the cost of identification and degrades the system performance. The paper proposes an efficient indexing technique that can scatter the effect of database escalation and maintains the system performance. It has proposed a fixed length feature vector built from each minutia, known as Coaxial Gaussian Track Code (CGTC). The proposed technique inserts feature vector into a Quantized Lookup Table (QLT) only once. As a result, it reduces both computational and memory costs. Since minutiae of all fingerprint images in the database are found to be well distributed in the quantized lookup table, it does not need rehashing. Experiments have been conducted over three fingerprint databases viz. FVC2002, FVC2004 and IITK-Sel500FP containing fingerprints from 100, 100 and 500 subjects respectively. Results have proven the superiority of the proposed indexing technique against well known geometric based indexing techniques.

A touch-less fingerphoto recognition system for mobile hand-held devices

Fingerphoto is an image of a human finger obtained with the help of an ordinary camera. Its acquisition is convenient and does not require any particular biometric scanner. The high degree of freedom in finger positioning introduces challenges to its recognition. This paper proposes a fingerphoto based human authentication system for mobile hand-held devices by using a non-conventional scale-invariant features. The system utilizes built-in camera of the mobile devices to acquire biometric sample and therefore, eliminates the dependence over specifics scanners. It can successfully handle some of the issues like orientation, rotation and lack of registration at the time of matching. It has achieved CRR of 96.67% and EER of 3.33% which is better than any other system available in the literature.

A heuristic technique for performance improvement of fingerprint based integrated biometric system

Integrated biometric system coherently connects multiple independent biometric systems to improve upon security and usability. But due to some involved factors the performance of overall system get degraded. This paper proposes a heuristic technique to improves the performance of fingerprint based integrated biometric system. One of the main advantage of the proposed technique is that it does not ask to modify the underline identification approach of the independent systems. The technique has been tested by constructing an integrated system with three commercial available independent biometric systems and the database used is IITK-Rural containing fingerprint images of 500 subjects collected over two sessions on three scanners. The proposed heuristics improves the equal error rate (EER) of integrated system from 21.78% to 15.67%.