V. A. Bharadi

Off-Line Signature Recognition Systems

Handwritten signature is one of the most widely used biometric traits for authentication of person as well as document. In this paper we discuss issues regarding off-line signature recognitions. We review existing techniques, their performance and method for feature extraction. We discuss a system designed using cluster based global features which is a multi algorithmic offline signature recognition system.

Gabor Filter Based Feature Vector for Dynamic Signature Recognition

Dynamic signature recognition is one of the commonly used biometric traits. In this paper we propose use of Gabor filters based feature for verification of dynamic signature. We incorporate the timing information available in the signature along with the Gabor filter response to generate the feature vector. Gabor filters have been widely used for image, texture analysis. Here we present analysis for the Gabor filter based feature vector of a dynamic signature.

Fingerprint Core Point Detection Algorithm using Orientation Field Based Multiple Features

Fingerprint recognition is a widely used biometric identification mechanism. In case of correlation based fingerprint recognition detection of a consistent registration point is a crucial issue; this point can be a core point of a fingerprint. Many techniques have been proposed but success rate is highly dependent on input used and accurate core point detection is still an open issue. Here we discuss an algorithm which is based on multiple features derived from the fingerprint which are collectively used for consistent core point detection. Here we use Orientation field, coherence, Poincare index for core point detection. Though all fingerprints don’t possess core point still this algorithm is useful to detect high curvature regions and gives high accuracy as it combines advantages form individual features. This algorithm is crucial in the development of correlation based Automatic Fingerprint Recognition System (AFIS).

Multimodal biometrics

Biometric products provide improved security over traditional electronic access control methods such as RFID tags, electronic keypads and some mechanical locks. They ensure that the authorized user is present in order for access to take place. The users authorized card or password pin cannot be stolen or lost to gain access. Common physical biometrics includes fingerprints, hand or palm geometry, retina, iris, or facial characteristics, whereas behavioural characteristics include signature, voice (which also has a physical component), keystroke pattern, and gait. While some technologies have gained more acceptance then others, it is beyond doubt that the field of access control biometrics has gained a measure of acceptance. Multimodal biometrics use a combination of different biometric recognition technologies In order for the biometrics to be ultra-secure and to provide more-than-average accuracy, more than one form of biometric identification is required. Hence the need arises for the use of multimodal biometrics. This uses a combination of different biometric recognition technologies. In certain situations, the user might find one form of biometric identification is not exact enough for identification. This can be the case with fingerprints, where at least 10% of the population have worn, cut or unrecognizable prints. Multimodal biometric technology uses more than one biometric identifier to compare the identity of the person. Therefore in the case of a system using say three technologies i.e. face mimic and voice. If one of the technologies is unable to identify, the system can still use the other two to accurately identify against. Multimodal technologies have been in use commercially since 1998. Multimodal biometric systems are those which utilize, or are capability of utilizing, more than one physiological or behavioral characteristic for enrollment, verification, or identification

Online Signature Recognition Using Software as a Service (SaaS) Model on Public Cloud

The signature recognition systems are widely used and measure of security and authenticity in terms of commercial as well as official transactions. The exciting signature recognition systems need a high configuration machine to perform multiple operations of feature vector extraction, enrollment and verification. These implementations are generally standalone and implemented on a single server based architecture, in this case even a single point of failure may occur. The standalone application are not scalable. With the increasing number users the biometric implementation has to be scalable and capable of handling large datasets for a large population. In this paper, a highly scalable, pluggable and faster cloud based online signature recognition system is proposed, which is capable of operating on enormous amounts of data, which, in turn, induces the need for sufficient storage capacity and significant processing power.

Iris Recognition Using Vector Quantization

In today’s world, where terrorist attacks are on the rise, employment of infallible security systems is a must. Iris recognition enjoys universality, high degree of uniqueness and moderate user co-operation. This makes Iris recognition systems unavoidable in emerging security & authentication mechanisms. We propose an iris recognition system based on vector quantization. The proposed system does not need any pre-processing and segmentation of the iris. We have tested LBG, Kekre’s Proportionate Error Algorithm (KPE) & Kekre’s Fast Codebook Generation Algorithm (KFCG) for the clustering purpose. From the results it is observed that KFCG requires 99.79% less computations as that of LBG and KPE. Further the KFCG method gives best performance with the accuracy of 89.10% outperforming LBG that gives accuracy around 81.25%. Performance of individual methods is evaluated and presented in this paper.

Signature Recognition using Cluster Based Global Features

In this paper we discuss an off-line signature recognition system designed using clustering techniques. These cluster based features are mainly morphological feature, they include Walsh coefficients of pixel distributions, Vector Quantization based codeword histogram, Grid & Texture information features and Geometric centers of a signature. In this paper we discuss the extraction and performance analysis of these features. We present the FAR, FRR achieved by the system using these features . We compare individual performance and overall system performance.

Finger-Knuckle-Print Region of Interest Segmentation Using Gradient Field Orientation & Coherence

Finger-knuckle-print is one of the emerging biometric traits. The region of interest is the area where the maximum information is centered, for a finger knuckle it is the area surrounding the knuckle region. A good system needs this region of interest as input for the feature vector extraction. In this method we present a novel approach for segmentation of Region of interest (ROI) of a finger-knuckle-print using gradient field orientation & its local field strength. This approach is fast and gives good results in case of shift in finger-knuckle-placement (translational shift).

Content Based Image Retreival Using Fusion of Gabor Magnitude and Modified Block Truncation Coding

Content-based means that the search makes use of the contents of the images themselves, rather than relying on human inputted metadata such as captions or keywords. By content-based techniques, a user can specify contents of interest in a query. The contents may be colors, textures, shapes, or the spatial layout of target images. We propose a CBIR system which is implemented with the help of combination of features. BTC is mainly used for image compression. The proposed method is a modification in original block truncation coding (BTC) for content based image retrieval system. Texture features are found by calculating the standard deviation of the Gabor filtered image. Gabor Filter & Modified Block Truncation Coding based feature vector is extracted, then compared with corresponding feature vector of images stored in the database. Images are retrieved based on the similarities features. The proposed method is tested on a database consisting of 1000 color images for test. All images in database are ranked according to their similarity to query image. To assess the retrieval effectiveness precision and recall as statistical comparison parameters for the MBTC and Gabor Filter based feature vector is used.

Fingerprint's Core Point Detection Using Orientation Field

Fingerprint recognition is a widely used biometricidentification mechanism. In case of correlation based fingerprintrecognition detection of a consistent registration point is a crucialissue; this point can be a core point of a fingerprint. Manytechniques have been proposed but success rate is highlydependent on input used and accurate core point detection is stillan open issue. Here we discuss a core point detection algorithmwhich is computationally simple and gives consistent detection ofa core point. The proposed technique is based on orientation fieldof the fingerprint which is calculated using gradient basedtechnique and optimized neighborhood averaging to generate asmoother orientation field, on which we operate a speciallydesigned mask for detecting core point as the orientation field inthe region of the core point is different than the other area.Though all fingerprints don’t possess core point still thisalgorithm is useful to detect high curvature regions. Thisalgorithm is helpful in the development of correlation basedAutomatic Fingerprint Recognition System (AFIS).