Farzin Deravi

A review of speech-based bimodal recognition

Speech recognition and speaker recognition by machine are crucial ingredients for many important applications such as natural and flexible human-machine interfaces. Most developments in speech-based automatic recognition have relied on acoustic speech as the sole input signal, disregarding its visual counterpart. However, recognition based on acoustic speech alone can be afflicted with deficiencies that preclude its use in many real-world applications, particularly under adverse conditions. The combination of auditory and visual modalities promises higher recognition accuracy and robustness than can be obtained with a single modality. Multimodal recognition is therefore acknowledged as a vital component of the next generation of spoken language systems. The paper reviews the components of bimodal recognizers, discusses the accuracy of bimodal recognition, and highlights some outstanding research issues as well as possible application domains.

The Multiscenario Multienvironment BioSecure Multimodal Database (BMDB)

A new multimodal biometric database designed and acquired within the framework of the European BioSecure Network of Excellence is presented. It is comprised of more than 600 individuals acquired simultaneously in three scenarios: 1 over the Internet, 2 in an office environment with desktop PC, and 3 in indoor/outdoor environments with mobile portable hardware. The three scenarios include a common part of audio/video data. Also, signature and fingerprint data have been acquired both with desktop PC and mobile portable hardware. Additionally, hand and iris data were acquired in the second scenario using desktop PC. Acquisition has been conducted by 11 European institutions. Additional features of the BioSecure Multimodal Database (BMDB) are: two acquisition sessions, several sensors in certain modalities, balanced gender and age distributions, multimodal realistic scenarios with simple and quick tasks per modality, cross-European diversity, availability of demographic data, and compatibility with other multimodal databases. The novel acquisition conditions of the BMDB allow us to perform new challenging research and evaluation of either monomodal or multimodal biometric systems, as in the recent BioSecure Multimodal Evaluation campaign. A description of this campaign including baseline results of individual modalities from the new database is also given. The database is expected to be available for research purposes through the BioSecure Association during 2008.

Region-based fractal image compression using heuristic search

Presents work carried out on fractal (or attractor) image compression. The approach relies on the assumption that image redundancy can be efficiently exploited through self-transformability. The algorithms described utilize a novel region-based partition of the image that greatly increases the compression ratios achieved over traditional block-based partitionings. Due to the large search spaces involved, heuristic algorithms are used to construct these region-based transformations. Results for three different heuristic algorithms are given. The results show that the region-based system achieves almost double the compression ratio of the simple block-based system at a similar decompressed image quality. For the Lena image, compression ratios of 41:1 can be achieved at a PSNR of 26.56 dB.

Face verification competition on the XM2VTS database

In the year 2000 a competition was organised to collect face verification results on an identical, publicly available data set using a standard evaluation protocol. The database used was the Xm2vts database along with the Lausanne protocol [14]. Four different institutions submitted results on the database which were subsequently published in [13]. Three years later, a second contest using the same dataset and protocol was organised as part of AVBPA 2003. This time round seven seperate institutions submitted results to the competition. This paper presents the results of the competition and shows that verification results on this protocol have increased in performance by a factor of 3.

Adaptive classifier integration for robust pattern recognition

The integration of multiple classifiers promises higher classification accuracy and robustness than can be obtained with a single classifier. This paper proposes a new adaptive technique for classifier integration based on a linear combination model. The proposed technique is shown to exhibit robustness to a mismatch between test and training conditions. It often outperforms the most accurate of the fused information sources. A comparison between adaptive linear combination and non-adaptive Bayesian fusion shows that, under mismatched test and training conditions, the former is superior to the latter in terms of identification accuracy and insensitivity to information source distortion.

Template-Free Biometric-Key Generation by Means of Fuzzy Genetic Clustering

Biometric authentication is increasingly gaining popularity in a wide range of applications. However, the storage of the biometric templates and/or encryption keys that are necessary for such applications is a matter of serious concern, as the compromise of templates or keys necessarily compromises the information secured by those keys. In this paper, we propose a novel method, which requires storage of neither biometric templates nor encryption keys, by directly generating the keys from statistical features of biometric data. An outline of the process is as follows: given biometric samples, a set of statistical features is first extracted from each sample. On each feature subset or single feature, we model the intra and interuser variation by clustering the data into natural clusters using a fuzzy genetic clustering algorithm. Based on the modelling results, we subsequently quantify the consistency of each feature subset or single feature for each user. By selecting the most consistent feature subsets and/or single features for each user individually, we generate the key reliably without compromising its relative security. The proposed method is evaluated on handwritten signature data and compared with related methods, and the results are very promising.

Integration of neural networks and expert systems for microscopic wear particle analysis

A loosely coupled integration of neural networks and expert systems, using simple message interaction, has been developed for the analysis of microscopic wear particles from machinery. The neural networks are used to classify particle features, whilst a knowledge based system is used for overall wear assessment (using the feature classifications). This type of integration maintains the individual strengths of neural networks and expert systems. The particle features are obtained from a computer vision system linked to the neural networks, and the wear assessment relies on a knowledge base derived from human experts. The system is adaptable, extendable, modular and fast.

A Memetic Fingerprint Matching Algorithm

Minutiae point pattern matching is the most common approach for fingerprint verification. Although many minutiae point pattern matching algorithms have been proposed, reliable automatic fingerprint verification remains as a challenging problem, both with respect to recovering the optimal alignment and the construction of an adequate matching function. In this paper, we develop a memetic fingerprint matching algorithm (MFMA) which aims to identify the optimal or near optimal global matching between two minutiae sets. Within the MFMA, we first introduce an efficient matching operation to produce an initial population of local alignment configurations by examining local features of minutiae. Then, we devise a hybrid evolutionary procedure by combining the use of the global search functionality of a genetic algorithm with a local improvement operator to search for the optimal or near optimal global alignment. Finally, we define a reliable matching function for fitness computation. The proposed algorithm was evaluated by means of a series of experiments conducted on the FVC2002 database and compared with previous work. Experimental results confirm that the MFMA is an effective and practical matching algorithm for fingerprint verification. The algorithm is faster and more accurate than a traditional genetic-algorithm-based method. It is also more accurate than a number of other methods implemented for comparison, though our method generally requires more computational time in performing fingerprint matching.

Comparison of shape features for the classification of wear particles

Abstract Wear particle shapes are divided into four classes: Regular, Irregular, Circular and Elongated. They have been classified here using back-propagation neural networks which have been trained using different sets of rotation-, scale- and translation-invariant shape features derived from particle boundaries. The features include: Fourier coefficients based on either boundary curvature analysis or XY co-ordinates of boundary points; statistical moments of the curvature distribution including standard deviation, skewness and kurtosis; and two general shape descriptions, aspect ratio and roundness. In order to evaluate the performances of the features, a series of tests have been carried out on a wear particle database, and the results are compared. The boundary-curvature-based Fourier descriptors produce a shape classifier with the highest performance. The neural network trained by the Fourier features derived from the boundary data provides a slightly lower classification rate which is similar to that achieved using three statistical moments combined with the two general shape features.

Biosignals for User Authentication - Towards Cognitive Biometrics?

Cognitive biometrics refers to a novel approach for user authentication/identification utilising biosignals which reflect the mental and emotional states of an individual. Specifically, current implementations rely on the use of the electroencephalogram (EEG), electrocardiogram (ECG), and the electro dermal response (EDR) as inputs into a traditional authentication scheme. The motivation for the deployment of biosignals resides in their potential uniqueness, universality, and their resistance to spoofing. The challenge with respect to cognitive biometrics based on biosignals is to enhance the information content of the acquired data. This paper presents a brief survey of the use of such biosignals to produce cognitive biometric systems for person recognition. The types of signals used and their claimed effectiveness is presented and compared. The paper concludes with a description of the challenges facing the deployment of cognitive biometrics, including sensor design issues and the need to extract information-rich and robust features.