Alisher Anatolyevich Kholmatov

Identity authentication using improved online signature verification method

We present a system for online handwritten signature verification, approaching the problem as a two-class pattern recognition problem. A test signatures authenticity is established by first aligning it with each reference signature for the claimed user, using dynamic time warping. The distances of the test signature to the nearest, farthest and template reference signatures are normalized by the corresponding mean values obtained from the reference set, to form a three-dimensional feature vector. This feature vector is then classified into one of the two classes (genuine or forgery). A linear classifier used in conjunction with the principal component analysis obtained a 1.4% error rate for a data set of 94 people and 619 test signatures (genuine signatures and skilled forgeries). Our method received the first place at SVC2004 with a 2.8% error rate.

Realization of correlation attack against the fuzzy vault scheme

User privacy and template security are major concerns in the use of biometric systems. These are serious concerns based on the fact that once compromised, biometric traits can not be canceled or reissued. The Fuzzy Vault scheme has emerged as a promising method to alleviate the template security problem. The scheme is based on binding the biometric template with a secret key and scrambling it with a large amount of redundant data, such that it is computationally infeasible to extract the secret key without possession of the biometric trait. It was recently claimed that the scheme is susceptible to correlation based attacks which assume the availability of two fuzzy vaults created using the same biometric data (e.g. two impressions of the same fingerprint) and suggests that correlating them would reveal the biometric data hidden inside. In this work, we implemented the fuzzy vault scheme using fingerprints and performed correlation attacks against a database of 400 fuzzy vaults (200 matching pairs). Given two matching vaults, we could successfully unlock 59% of them within a short time. Furthermore, it was possible to link an unknown vault to a short list containing its matching pair, for 41% of all vaults. These results prove the claim that the fuzzy vault scheme without additional security measures is indeed vulnerable to correlation attacks.

SUSIG: an on-line signature database, associated protocols and benchmark results

We present a new online signature database (SUSIG). The database consists of two parts that are collected using different pressure-sensitive tablets (one with and the other without an LCD display). A total of 100 people contributed to each part, resulting in a database of more than 3,000 genuine signatures and 2,000 skilled forgeries. The genuine signatures in the database are real signatures of the contributors. In collecting skilled forgeries, forgers were shown the signing process on the monitor and were given a chance to practice. Furthermore, for a subset of the forgeries (highly skilled forgeries), this animation was mapped onto the LCD screen of the tablet so that the forgers could trace over the mapped signature. Forgers in this group were also informed of how close they were to the reference signature, so that they could improve their forgery quality. We describe the signature acquisition process and several verification protocols for this database. We also report the performance of a state-of-the-art signature verification system using the associated protocols. The results show that the highly skilled forgery set is significantly more difficult compared to the skilled forgery set, providing researchers with challenging forgeries. The database is available through http://biometrics.sabanciuniv.edu.

Online signature verification using Fourier descriptors

We present a novel online signature verification system based on the Fast Fourier Transform. The advantage of using the Fourier domain is the ability to compactly represent an online signature using a fixed number of coefficients. The fixed-length representation leads to fast matching algorithms and is essential in certain applications. The challenge on the other hand is to find the right preprocessing steps and matching algorithm for this representation. We report on the effectiveness of the proposed method, along with the effects of individual preprocessing and normalization steps, based on comprehensive tests over two public signature databases. We also propose to use the pen-up duration information in identifying forgeries. The best results obtained on the SUSIG-Visual subcorpus and the MCYT-100 database are 6.2% and 12.1% error rate on skilled forgeries, respectively. The fusion of the proposed system with our state-of-the-art Dynamic Time Warping (DTW) system lowers the error rate of the DTW system by up to about 25%. While the current error rates are higher than state-of-the-art results for these databases, as an approach using global features, the system possesses many advantages. Considering also the suggested improvements, the FFT system shows promise both as a stand-alone system and especially in combination with approaches that are based on local features.

Offline signature verification using classifier combination of HOG and LBP features

We present an offline signature verification system based on a signatures local histogram features. The signature is divided into zones using both the Cartesian and polar coordinate systems and two different histogram features are calculated for each zone: histogram of oriented gradients (HOG) and histogram of local binary patterns (LBP).

Biometric authentication using online signatures

We overview biometric authentication and present a system for on-line signature verification, approaching the problem as a two-class pattern recognition problem. During enrollment, reference signatures are collected from each registered user and cross aligned to extract statistics about that user’s signature. A test signature’s authenticity is established by first aligning it with each reference signature for the claimed user. The signature is then classified as genuine or forgery, according to the alignment scores which are normalized by reference statistics, using standard pattern classification techniques. We experimented with the Bayes classifier on the original data, as well as a linear classifier used in conjunction with Principal Component Analysis (PCA). The classifier using PCA resulted in a 1.4% error rate for a data set of 94 people and 495 signatures (genuine signatures and skilled forgeries).

Biometric cryptosystem using online signatures

Biometric cryptosystems combine cryptography and biometrics to benefit from the strengths of both fields. In such systems, while cryptography provides high and adjustable security levels, biometrics brings in non-repudiation and eliminates the need to remember passwords or to carry tokens etc. In this work, we present a biometric cryptosystem which uses online signatures, based on the fuzzy vault scheme of Jules et al. The fuzzy vault scheme releases a previously stored key when the biometric data presented for verification matches the previously stored template hidden in a vault. The online signature of a person is a behavioral biometric which is widely accepted as the formal way of approving documents, bank transactions, etc. As such, biometric-based key release using online signatures may have many application areas. We extract minutiae points (trajectory crossings, endings and points of high curvature) from online signatures and use those during the locking & unlocking phases of the vault. We present our preliminary results and demonstrate that high security level (128 bit encryption key length) can be achieved using online signatures.

Multi-biometric templates using fingerprint and voice

As biometrics gains popularity, there is an increasing concern about privacy and misuse of biometric data held in central repositories. Furthermore, biometric verification systems face challenges arising from noise and intra-class variations. To tackle both problems, a multimodal biometric verification system combining fingerprint and voice modalities is proposed. The system combines the two modalities at the template level, using multibiometric templates. The fusion of fingerprint and voice data successfully diminishes privacy concerns by hiding the minutiae points from the fingerprint, among the artificial points generated by the features obtained from the spoken utterance of the speaker. Equal error rates are observed to be under 2% for the system where 600 utterances from 30 people have been processed and fused with a database of 400 fingerprints from 200 individuals. Accuracy is increased compared to the previous results for voice verification over the same speaker database.

Performance Analysis of the CCD Pixel Binning Option in Particle-Image Velocimetry Measurements

This paper proposes convenient methods to increase the dynamic speed range in particle-image velocimetry (PIV) measurements, which employ a charge-coupled device (CCD) camera binning option. Although the binning procedure decreases spatial resolution along specified dimensions, its ability to increase the camera frame rate and preserve the field-of-view are important advantages, which need to be thoroughly investigated. In order to demonstrate the advantages of the CCD binning option, we have carried out experiments both on static images of in-plane particle displacements and on dynamic images of real-fluid flows. In the first experiment, we have analyzed static images of 0.5, 1, and 1.9 μm size fluorescent polystyrene microparticles placed on thick quartz glass plate and illuminated by high-power LED. The in-plane images were captured at various CCD binning options, the distance between particles was then calculated using cross-correlation analysis and a subpixel interpolation scheme based on a Gaussian filter. In the second experiment, the fluid flow in a 30 × 300 × 50 000 μm microchannel was recorded at various CCD binning modes, and then, evaluated using ensemble-averaged normalized cross-correlation analysis with Gaussian subpixel interpolation. Velocity profiles obtained at various CCD binning modes were compared with those obtained at the normal mode. Error analysis has shown that despite the loss of the spatial resolution, the advantages of pixel binning, specifically increased sensitivity and a total full-frame rate, can be useful in PIV measurements, especially in laminar-fluid flows.

The use of CCD pixel binning in PIV measurements

In this work, we study the effects of a CCD camera binning option, which increases camera frame rate throughput at the expense of loosing spatial resolution, on the Particle Image Velocimetry measurements. The camera frame rate defines upper bound on a speed of a flow a PIV system can measure. We have carried our experiments on the real images of the 1 µm size fluorescence polystyrene microparticles placed onto a thick quarts glass plate and illuminated with the high-power LED. The in-plane images were captured at various CCD binning factors and the distances between particles were calculated using cross-correlation analysis with a sub-pixel interpolation scheme based on the Gaussian regression. As a result of this study, we show that despite the decrease in the spatial resolution, the advantages of the pixel binning, such as increase in sensitivity and the total full frame rate, can be useful for LED illuminated PIV measurements, especially in laminar fluid flows.