George W. Quinn

Distinguishing identical twins by face recognition

The paper measures the ability of face recognition algorithms to distinguish between identical twin siblings. The experimental dataset consists of images taken of 126 pairs of identical twins (252 people) collected on the same day and 24 pairs of identical twins (48 people) with images collected one year apart. In terms of both the number of paris of twins and lapsed time between acquisitions, this is the most extensive investigation of face recognition performance on twins to date. Recognition experiments are conducted using three of the top submissions to the Multiple Biometric Evaluation (MBE) 2010 Still Face Track [1]. Performance results are reported for both same day and cross year matching. Performance results are broken out by lighting conditions (studio and outside); expression (neutral and smiling); gender and age. Confidence intervals were generated by a bootstrap method. This is the most detailed covariate analysis of face recognition of twins to date.

IREX III - Performance of Iris Identification Algorithms

Disclaimer Specific hardware and software products identified in this report were used in order to perform the evaluations described in this document. In no case does identification of any commercial product, trade name, or vendor, imply recommendation or endorsement by the National Institute of Standards and Technology, nor does it imply that the products and equipment identified are necessarily the best available for the purpose.

Double Trouble: Differentiating Identical Twins by Face Recognition

Facial recognition algorithms should be able to operate even when similar-looking individuals are encountered, or even in the extreme case of identical twins. An experimental data set comprised of 17486 images from 126 pairs of identical twins (252 subjects) collected on the same day and 6864 images from 120 pairs of identical twins (240 subjects) with images taken a year later was used to measure the performance on seven different face recognition algorithms. Performance is reported for variations in illumination, expression, gender, and age for both the same day and cross-year image sets. Regardless of the conditions of image acquisition, distinguishing identical twins are significantly harder than distinguishing subjects who are not identical twins for all algorithms.

Modest proposals for improving biometric recognition papers

We present practical recommendations for improving the clarity, transparency, and usefulness of many biometric papers. Several of the recommendations can be enabled by preparing a publicly available library of state of the art Receiver Operating Characteristics (ROCs). We propose such a library and invite suggestions on its details.

IREX VI: mixed-effects longitudinal models for iris ageing: response to Bowyer and Ortiz

Bowyer and Ortiz, in their study ‘A Critical Examination of the IREX VI Results’, make seven criticisms of the authors application of linear mixed-effects models to longitudinally collected iris recognition Hamming distances. We reject these as either irrelevant, misinterpretations, or qualitatively correct, but quantitatively irrelevant.

Standard Iris Storage Formats

Iris recognition standards are open specifications for iris cameras, iris image properties, and iris image records. Biometric data standards are a necessity for applications in which a consumer of a data record must process biometric input from an arbitrary producer. The archetype for standard iris storage formats has been the flight of standards already developed for the storage of biometric data on electronic passports.

The one-to-many multi-modal fusion challenge

The One-to-many Multi-modal Fusion Challenge is presented, with the aim of promoting academic research into one-to-many methods of fusion for large-scale biometric systems. Although most research into fusion has been conducted using verification (one-to-one) comparison results, there is greater demand among government agencies for one-to-many fusion. The fusion challenge makes commercial iris and face matching results available to the public. Results are computed over operational data. Specific challenges that are relevant to deployers of biometric systems are put forth, and an adaptation of Neyman-Pearson fusion is used to compute baseline results for some of the challenges. The results show that there is potential to improve recognition accuracy by fusing comparison results from multiple iris algorithms, even when one of the algorithms is considerably more accuracy than the other.

False Matches and Non-independence of Face Recognition Scores

Although face recognition algorithms have made significant progress over the years, they still lack the accuracy to accomplish many of the more demanding tasks that have been proposed. To address this problem, several authors have suggested supplementing biometric systems with soft biometric information such as age, height, and sex to improve the overall accuracy of the system. However, the improvement is contingent on the matcher not already intrinsically factoring the soft biometric information into its comparison score. In fact, since soft biometric traits tend to be reflected in the physical characteristics of the face, such traits are expected to correlate with face matcher scores. In this paper, two methods are used to explore the statistical relationship between soft biometric traits and non-match scores generated by a leading commercial face recognition algorithm. The first method uses a generalized linear model (GLM) to determine how age, sex, and nationality covary with the probability of a false match. The second method uses sample partitioning for a more direct presentation of how the probability of a false match varies for different combinations of soft biometric values. Results indicate that age, nationality, and sex have a statistically significant effect on non-match scores. We explore what makes soft biometric information useful for the purpose of improving the accuracy of a biometric system under the assumption that the additional subject information is used to filter comparisons between subjects that have incompatible soft biometric characteristics (e.g. comparisons between men and women).