Karl Ricanek

MORPH: a longitudinal image database of normal adult age-progression

This paper details MORPH a longitudinal face database developed for researchers investigating all facets of adult age-progression, e.g. face modeling, photo-realistic animation, face recognition, etc. This database contributes to several active research areas, most notably face recognition, by providing: the largest set of publicly available longitudinal images; longitudinal spans from a few months to over twenty years; and, the inclusion of key physical parameters that affect aging appearance. The direct contribution of this data corpus for face recognition is highlighted in the evaluation of a standard face recognition algorithm, which illustrates the impact that age-progression, has on recognition rates. Assessment of the efficacy of this algorithm is evaluated against the variables of gender and racial origin. This work further concludes that the problem of age-progression on face recognition (FR) is not unique to the algorithm used in this work

Age estimation using Active Appearance Models and Support Vector Machine regression

In this paper, we introduce a novel age estimation technique that combines Active Appearance Models (AAMs) and Support Vector Machines (SVMs), to dramatically improve the accuracy of age estimation over the current state-of-the-art techniques. In this method, characteristics of the input images, face image, are interpreted as feature vectors by AAMs, which are used to discriminate between childhood and adulthood, prior to age estimation. Faces classified as adults are passed to the adult age-determination function and the others are passed to the child age-determination function. Compared to published results, this method yields the highest accuracy recognition rates, both in overall mean-absolute error (MAE) and mean-absolute error for the two periods of human development: childhood and adulthood.

Aspects of Age Variation in Facial Morphology Affecting Biometrics

There is a great degree of variation that occurs in the face during aging of adults that will affect outcomes for face- based biometric systems. These changes have been studied sporadically in anthropological research and have received even less attention in biometric-related literature. This paper presents a summary of recent research that spans biometric, forensic, and anthropologic literature in an attempt to unify a variety of findings related to adult aging, discusses work in synthesizing images of aged faces and its relation to the anthropological findings, and also presents work demonstrating a need for further study in this area to improve face-based biometric techniques. Only age-invariant or aging-aware methods will have the best success in longer stretches of time.

Fusing with context: A Bayesian approach to combining descriptive attributes

For identity related problems, descriptive attributes can take the form of any information that helps represent an individual, including age data, describable visual attributes, and contextual data. With a rich set of descriptive attributes, it is possible to enhance the base matching accuracy of a traditional face identification system through intelligent score weighting. If we can factor any attribute differences between people into our match score calculation, we can deemphasize incorrect results, and ideally lift the correct matching record to a higher rank position. Naturally, the presence of all descriptive attributes during a match instance cannot be expected, especially when considering non-biometric context. Thus, in this paper, we examine the application of Bayesian Attribute Networks to combine descriptive attributes and produce accurate weighting factors to apply to match scores from face recognition systems based on incomplete observations made at match time. We also examine the pragmatic concerns of attribute network creation, and introduce a Noisy-OR formulation for streamlined truth value assignment and more accurate weighting. Experimental results show that incorporating descriptive attributes into the matching process significantly enhances face identification over the baseline by up to 32.8%.

Cross-Age Face Recognition on a Very Large Database: The Performance versus Age Intervals and Improvement Using Soft Biometric Traits

Facial aging can degrade the face recognition performance dramatically. Traditional face recognition studies focus on dealing with pose, illumination, and expression (PIE) changes. Considering a large span of age difference, the influence of facial aging could be very significant compared to the PIE variations. How big the aging influence could be? What is the relation between recognition accuracy and age intervals? Can soft biometrics be used to improve the face recognition performance under age variations? In this paper we address all these issues. First, we investigate the face recognition performance degradation with respect to age intervals between the probe and gallery images on a very large database which contains about 55,000 face images of more than 13,000 individuals. Second, we study if soft biometric traits, e.g., race, gender, height, and weight, could be used to improve the cross-age face recognition accuracies, and how useful each of them could be.

The effect of normal adult aging on standard PCA face recognition accuracy rates

The issue of face aging has not been explicitly focused upon in the research on face recognition (FR) systems. What has been introduced by a few researchers is the impact of a probe against a match of different acquisition dates; the time span between probe and match image acquisition has not historically been sufficiently large enough to fully explore the impacts of age-progression on performance rates. In this work, we address the impacts of age-progression, which includes both structural and texture changes, on the standard PCA FR algorithm. A face database designed specifically to address the issues of age-progression is used with the FERET database. This work examines why the PCA FR system, and possibly other appearance based FR systems, is diminished recognition rates.

Face age estimation using model selection

Face age estimation is a difficult problem due to the dynamics of facial aging and its complex interactions owing to genetics and behavior factors. In this work we develop a robust age estimation system tuned by model selection that outperforms all prior systems on the FG-NET face database. We study various model selection methods systematically to determine the best selection methods among Least Angle Regression (LAR), Principle Component Analysis (PCA), and Locality Preserving Projections (LPP) for age estimation. Our performance analysis on PAL and FG-NET databases suggest that age estimation with LAR or LPP outperforms the full feature model. Furthermore, this work develops a novel operator named “graph age preserving” (GAP) to build a neighborhood graph for LPP for age estimation.

Letters: Laplacian bidirectional PCA for face recognition

Two-dimensional principal components analysis (2DPCA) needs more coefficients than principal components analysis (PCA) for image representation and hence needs more time for classification. The bidirectional PCA (BDPCA) is proposed to overcome these drawbacks of 2DPCA. Both 2DPCA and BDPCA, however, can work only in Euclidean space. In this paper, we propose Laplacian BDPCA (LBDPCA) to enhance the robustness of BDPCA by extending it to non-Euclidean space. Experimental results on representative face databases show that LBDPCA works well and it surpasses BDPCA.

LBP-based periocular recognition on challenging face datasets

AbstractThis work develops a novel face-based matcher composed of a multi-resolution hierarchy of patch-based feature descriptors for periocular recognition - recognition based on the soft tissue surrounding the eye orbit. The novel patch-based framework for periocular recognition is compared against other feature descriptors and a commercial full-face recognition system against a set of four uniquely challenging face corpora. The framework, hierarchical three-patch local binary pattern, is compared against the three-patch local binary pattern and the uniform local binary pattern on the soft tissue area around the eye orbit. Each challenge set was chosen for its particular non-ideal face representations that may be summarized as matching against pose, illumination, expression, aging, and occlusions. The MORPH corpora consists of two mug shot datasets labeled Album 1 and Album 2. The Album 1 corpus is the more challenging of the two due to its incorporation of print photographs (legacy) captured with a variety of cameras from the late 1960s to 1990s. The second challenge dataset is the FRGC still image set. Corpus three, Georgia Tech face database, is a small corpus but one that contains faces under pose, illumination, expression, and eye region occlusions. The final challenge dataset chosen is the Notre Dame Twins database, which is comprised of 100 sets of identical twins and 1 set of triplets. The proposed framework reports top periocular performance against each dataset, as measured by rank-1 accuracy: (1) MORPH Album 1, 33.2%; (2) FRGC, 97.51%; (3) Georgia Tech, 92.4%; and (4) Notre Dame Twins, 98.03%. Furthermore, this work shows that the proposed periocular matcher (using only a small section of the face, about the eyes) compares favorably to a commercial full-face matcher.

Image classification using kernel collaborative representation with regularized least square

Sparse representation based classification (SRC) has received much attention in computer vision and pattern recognition. SRC codes a testing sample by sparse linear combination of all the training samples and classifies the testing sample into the class with the minimum representation error. Recently, Zhang analyzes the working mechanism of SRC and points out that it is the collaborative representation but not the L1-norm sparsity that makes SRC powerful. Based on the analysis, they propose a very simple and much more efficient classification scheme, called collaborative representation based classification with regularized least square (CRC_RLS). CRC_RLS is a linear method in nature. Here we propose a kernel collaborative representation based classification with regularized least square (Kernel CRC_RLS, KCRC_RLS) by implicitly mapping the sample into high-dimensional space via kernel tricks. Our approach is highly motivated by the kernel methods which can capture the nonlinear similarity among samples and have been successfully applied in pattern recognition and machine learning. The experimental results on the CENPAMI handwritten digital database, ETH80 database, FERET face database, ORL database, AR face database, demonstrate that Kernel CRC_RLS is effective in classification, leading to promising performance.