A measure of information gained through biometric systems

We propose a measure of information gained through biometric matching systems. Firstly, we discuss how the information about the identity of a person is derived from biometric samples through a biometric system, and define the “biometric system entropy” or BSE based on mutual information. We present several theoretical properties and interpretations of the BSE, and show how to design a biometric system which maximizes the BSE. Then we prove that the BSE can be approximated asymptotically by the relative entropy D(f_G(x)∥f_I(x)) where f_G(x) and f_I(x) are probability mass functions of matching scores between samples from individuals and among population. We also discuss how to evaluate the BSE of a biometric system and show experimental evaluation of the BSE of face, fingerprint and multimodal biometric systems.     

A new Probe Guided Mutation operator and its application for solving the cardinality constrained portfolio optimization problem

This paper revisits the classical Polynomial Mutation (PLM) operator and proposes a new probe guided version of the PLM operator designed to be used in conjunction with Multiobjective Evolutionary Algorithms (MOEAs). The proposed Probe Guided Mutation (PGM) operator is validated by using data sets from six different stock markets. The performance of the proposed PGM operator is assessed in comparison with the one of the classical PLM with the assistance of the Non-dominated Sorting Genetic Algorithm II (NSGAII) and the Strength Pareto Evolutionary Algorithm 2 (SPEA2). The evaluation of the performance is based on three performance metrics, namely Hypervolume, Spread and Epsilon indicator. The experimental results reveal that the proposed PGM operator outperforms with confidence the performance of the classical PLM operator for all performance metrics when applied to the solution of the cardinality constrained portfolio optimization problem (CCPOP). We also calculate the True Efficient Frontier (TEF) of the CCPOP by formulating the CCPOP as a Mixed Integer Quadratic Program (MIQP) and we compare the relevant results with the approximate efficient frontiers that are generated by the proposed PGM operator. The results confirm that the PGM operator generates near optimal solutions that lie very close or in certain cases overlap with the TEF.     

Automatic classification and prediction models for early Parkinson’s disease diagnosis from SPECT imaging

Early and accurate diagnosis of Parkinson’s disease (PD) is important for early management, proper prognostication and for initiating neuroprotective therapies once they become available. Recent neuroimaging techniques such as dopaminergic imaging using single photon emission computed tomography (SPECT) with ¹²³I-Ioflupane (DaTSCAN) have shown to detect even early stages of the disease. In this paper, we use the striatal binding ratio (SBR) values that are calculated from the ¹²³I-Ioflupane SPECT scans (as obtained from the Parkinson’s progression markers initiative (PPMI) database) for developing automatic classification and prediction/prognostic models for early PD. We used support vector machine (SVM) and logistic regression in the model building process. We observe that the SVM classifier with RBF kernel produced a high accuracy of more than 96% in classifying subjects into early PD and healthy normal; and the logistic model for estimating the risk of PD also produced high degree of fitting with statistical significance indicating its usefulness in PD risk estimation. Hence, we infer that such models have the potential to aid the clinicians in the PD diagnostic process.     

Efficient object detection based on selective attention

In this paper, we make use of biologically inspired selective attention to improve the efficiency and performance of object detection under clutter. At first, we propose a novel bottom-up attention model. We argue that heuristic feature selection based on bottom-up attention can stably select out invariant and discriminative features. With these selected features, performance of object detection can be improved apparently and stably. Then we propose a novel concept of saccade map based on bottom-up attention to simulate the saccade (eye movements) in vision. Sliding within saccade map to detect object can significantly reduce computational complexity and apparently improve performance because of the effective filtering for distracting information. With these ideas, we present a general framework for object detection through integrating bottom-up attention. Through evaluating on UIUC cars and Weizmann–Shotton horses we show state-of-the-art performance of our object detection model.     

An efficient and accurate approach of circular object detection in color images

Object detection is a critical step of many image recognition systems. In this paper, we discuss the problem of circular shape object detection in still color images. An isotropic edge detector merged with spatial information and region based analysis is employed to extract image edge and obtain accurate gradient information of edge pixels, which assures the high accuracy of the subsequent circle detection. Then three circle parameters are estimated efficiently with only one 2-dimensional accumulator array and one 1-dimensional accumulator array, which greatly reduces the storage requirements and time complexity of our approach. Experimental results show that our method is robust in locating objects with complete or incomplete or concentric circle boundary in real color images without any prior knowledge.     

Fast fingerprint identification for large databases

Fingerprint matching has emerged as an effective tool for human recognition due to the uniqueness, universality and invariability of fingerprints. Many different approaches have been proposed in the literature to determine faithfully if two fingerprint images belong to the same person. Among them, minutiae-based matchers highlight as the most relevant techniques because of their discriminative capabilities, providing precise results. However, performing a fingerprint identification over a large database can be an inefficient task due to the lack of scalability and high computing times of fingerprint matching algorithms.In this paper, we propose a distributed framework for fingerprint matching to tackle large databases in a reasonable time. It provides a general scheme for any kind of matcher, so that its precision is preserved and its time of response can be reduced.To test the proposed system, we conduct an extensive study that involves both synthetic and captured fingerprint databases, which have different characteristics, analyzing the performance of three well-known minutiae-based matchers within the designed framework. With the available hardware resources, our distributed model is able to address up to 400 000 fingerprints in approximately half a second. Additional details are provided at http://sci2s.ugr.es/ParallelMatching.