David S. Bolme Publications

This paper introduces a class of correlation filters called Average of Synthetic Exact Filters (ASEF). For ASEF, the correlation output is completely specified for each training image. This is in marked contrast to prior methods such as Synthetic Discriminant Functions (SDFs) which only specify a single output value per training image. Advantages of ASEF training include: insenitivity to over-fitting, greater flexibility with regard to training images, and more robust behavior in the presence of structured backgrounds. The theory and design of ASEF filters is presented using eye localization on the FERET database as an example task. ASEF is compared to other popular correlation filters including SDF, MACE, OTF, and UMACE, and with other eye localization methods including Gabor Jets and the OpenCV Cascade Classifier. ASEF is shown to outperform all these methods, locating the eye to within the radius of the iris approximately 98.5% of the time.

A study is presented showing how three state-of-the-art algorithms from the Face Recognition Vendor Test 2006 (FRVT 2006) are effected by factors related to face images and people. The recognition scenario compares highly controlled images to images taken of people as they stand before a camera in settings such as hallways and outdoors in front of buildings. A Generalized Linear Mixed Model (GLMM) is used to estimate the probability an algo- rithm successfully verifies a person conditioned upon the factors included in the study. The factors associated with people are: gender, race, age and whether they wear glasses. The factors associated with images are: the size of the face, edge density and region density. The setting, indoors versus out- doors, is also a factor. Edge density can change the estimated probability of verification dramatically, for example from about 0.15 to 0.85. However, this effect is not consistent across algorithm or setting. This finding shows that simple measurable factors are capable of characterizing face quality; however, these factors typically interact with both algorithm and setting.

The goal of the Multiple Biometrics Grand Challenge (MBGC) is to improve the performance of face and iris recognition technology from biometric samples acquired under unconstrained conditions. The MBGC is organized into three challenge problems. Each challenge problem relaxes the acquisition constraints in different directions. In the Portal Challenge Problem, the goal is to recognize people from near-infrared (NIR) and high definition (HD) video as they walk through a portal. Iris recognition can be performed from the NIR video and face recognition from the HD video. The availability of NIR and HD modalities allows for the development of fusion algorithms. The Still Face Challenge Problem has two primary goals. The first is to improve recognition performance from frontal and off angle still face images taken under uncontrolled indoor and outdoor lighting. The second is to improve recognition performance on still frontal face images that have been resized and compressed, as is required for electronic passports. In the Video Challenge Problem, the goal is to recognize people from video in unconstrained environments. The video is unconstrained in pose, illumination, and camera angle. All three challenge problems include a large data set, experiment descriptions, ground truth, and scoring code.

This paper presents a meta-analysis for covariates that affect performance of face recognition algorithms. Our review of the literature found six covariates for which multiple studies reported effects on face recognition performance. These are: age of the person, elapsed time between images, gender of the person, the person's expression, the resolution of the face images, and the race of the person. The results presented are drawn from 25 studies conducted over the past 12 years. There is near complete agreement between all of the studies that older people are easier to recognize than younger people, and recognition performance begins to degrade when images are taken more than a year apart. While individual studies find men or women easier to recognize, there is no consistent gender effect. There is universal agreement that changing expression hurts recognition performance. If forced to compare different expressions, there is still insufficient evidence to conclude that any particular expression is better than another. Higher resolution images improve performance for many modern algorithms. Finally, given the studies summarized here, no clear conclusions can be drawn about whether one racial group is harder or easier to recognize than another.

FaceL is a simple and fun face recognition system that labels faces in live video from an iSight camera or webcam. FaceL presents a window with a few controls and annotations displayed over the live video feed. The annotations indicate detected faces, positions of eyes, and after training, the names of enrolled people. Enrollment is video based, capturing many images per person. FaceL does a good job of distinguishing between a small set of people in fairly uncontrolled settings and incorporates a novel incremental training capability. The system is very responsive, running at over 10 frames per second on modern hardware. FaceL is open source and can be downloaded from http://pyvision.sourceforge.net/facel.

Our goal is to enable an individual analyst to utilize and benefit from millions of visualization instances created by a community of analysts. A visualization instance is the combination of a specific set of data and a specific configuration of a visualization providing a visual depiction of that data. As the variety and number of visualization techniques and tools continues to increase, and as users increasingly adopt these tools, more visualization instances will be created (today, perhaps only viewed for a moment and thrown away) during the solution of analysis tasks. This paper discusses what fraction of these visualization instances are worth keeping and why, and argues that keeping more (or all) visualization instances has high value and very low cost. Even if a small fraction is retained the result over time is still a large number of visualization instances and the issue remains, how can users utilize them? This paper describes what new functionality users need to utilize all those visualization instances, illustrated by examples using an information workspace tool based on zoomable user interface principles. The paper concludes with a concise set of principles for future analysis tools that utilize spatial organization of large numbers of visualization instances.

In this paper we present a collection of C and C++ biometric performance benchmark algorithms called FacePerf. The benchmark includes three different face recognition algo- rithms that are historically important to the face recognition community: Haar-based face detection, Principal Components Analysis, and Elastic Bunch Graph Matching. The algorithms are fast enough to be useful in realtime systems; however, improving performance would allow the algorithms to process more images or search larger face databases. Bottlenecks for each phase in the algorithms have been identified. A cosine approximation was able to reduce the execution timplementation by 32%.

This paper presents a bimodal identification sys- tem using text based term vectors and EBGM face recognition. Identification was tested on a database of 118 celebrities down- loaded from the internet. The dataset contained multiple images and two biographies for each person. Text based identification had a 100% identification rate for the full biographies. When the text data was artificially restricted to six sentences per subject, rank one identification rates were similar to face recognition (approx. 22%). In this restricted case, combining text identification and face identification showed a significant improvement in the identification rate over either method alone.

The CSU Face Identification Evaluation System includes standardized image preprocessing software, four distinct face recognition algorithms, analysis tools to study algorithm performance, and Unix shell scripts to run standard experiments. All code is written in ANSII C. The four algorithms provided are principle components analysis (PCA), a.k.a eigenfaces, a combined principle components analysis and linear discriminant analysis algorithm (PCA + LDA), an intrapersonal/extrapersonal image difference classifier (IIDC), and an elastic bunch graph matching (EBGM) algorithm. The PCA + LDA, IIDC, and EBGM algorithms are based upon algorithms used in the FERET study contributed by the University of Maryland, MIT, and USC, respectively. One analysis tool generates cumulative match curves; the other generates a sample probability distribution for recognition rate at recognition rank 1, 2, etc., using Monte Carlo sampling to generate probe and gallery choices. The sample probability distributions at each rank allow standard error bars to be added to cumulative match curves. The tool also generates sample probability distributions for the paired difference of recognition rates for two algorithms. Whether one algorithm consistently outperforms another is easily tested using this distribution. The CSU Face Identification Evaluation System is available through our Web site and we hope it will be used by others to rigorously compare novel face identification algorithms to standard algorithms using a common implementation and known comparison techniques.

A generalized linear mixed model is used to estimate how rank 1 recognition of human faces with a PCA+LDA algorithm is affected by the choice of distance metric, image size, PCA space dimensionality, supplemental training and inclusion of subjects in the training. Random effects for replicated training sets and for repeated measures on people were included in the model. Results indicate between people variation was a dominant source of variability, and that there was moderate correlation within people. Statistically significant effects and interactions were found for all configuration factors except image size. Changes to the PCA+LDA configuration only improved recognition for subjects who had images included in the training data. For subjects not included in training, no configuration changes were helpful. This study is instructive for what it reveals about PCA+LDA. It is also a model for how to conduct such studies. For example, by accounting for subject variation as a random effect and explicitly looking for interaction effects, we are able to discern effects that might otherwise have been masked by subject variation and interaction effects.

Abstract. The CSU Face Identification Evaluation System provides standard face recognition algorithms and standard statistical methods for comparing face recognition algorithms. The system includes standardized image pre-processing software, three distinct face recognition algorithms, analysis software to study algorithm performance, and Unix shell scripts to run standard experiments. All code is written in ANSI C. The preprocessing code replicates feature of pre-processing used in the FERET evaluations. The three algorithms provided are Principle Components Analysis (PCA), a.k.a Eigenfaces, a combined Principle Components Analysis and Linear Discriminant Analysis algorithm (PCA+LDA), and a Bayesian Intrapersonal/Extrapersonal Classifier (BIC). The PCA+LDA and BIC algorithms are based upon algorithms used in the FERET study contributed by the University of Maryland and MIT respectively. There are two analysis. The first takes as input a set of probe images, a set of gallery images, and similarity matrix produced by one of the three algorithms. It generates a Cumulative Match Curve of recognition rate versus recognition rank. The second analysis tool generates a sample probability distribution for recognition rate at recognition rank 1, 2, etc. It takes as input multiple images per subject, and uses Monte Carlo sampling in the space of possible probe and gallery choices. This procedure will, among other things, add standard error bars to a Cumulative Match Curve. The System is available through our website and we hope it will be used by others to rigorously compare novel face identification algorithms to standard algorithms using a common implementation and known comparison techniques.

Some people's faces are easier to recognize than others, but it is not obvious what subject-specific factors make individual faces easy or difficult to recognize. This study considers 11 factors that might make recognition easy or difficult for 1,072 human subjects in the FERET dataset. The specific factors are: race (white, Asian, African-American, or other), gender, age (young or old), glasses (present or absent), facial hair (present or absent), bangs (present or absent), mouth (closed or other), eyes (open or other), complexion (clear or other), makeup (present or absent), and expression (neutral or other). An ANOVA is used to determine the relationship between these subject covariates and the distance between pairs of images of the same subject in a standard Eigenfaces subspace. Some results are not terribly surprising. For example, the distance between pairs of images of the same subject increases for people who change their appearance, e.g., open and close their eyes, open and close their mouth or change expression. Thus changing appearance makes recognition harder. Other findings are surprising. Distance between pairs of images for subjects decreases for people who consistently wear glasses, so wearing glasses makes subjects more recognizable. Pairwise distance also decreases for people who are either Asian or African-American rather than white. A possible shortcoming of our analysis is that minority classifications such as African-Americans and wearers-of-glasses are underrepresented in training. Followup experiments with balanced training addresses this concern and corroborates the original findings. Another possible shortcoming of this analysis is the novel use of pairwise distance between images of a single person as the predictor of recognition difficulty. A separate experiment confirms that larger distances between pairs of subject images implies a larger recognition rank for that same pair of images, thus confirming that the subject is harder to recognize.

The CSU Face Identification Evaluation System provides standard face recognition algorithms and stan- dard statistical methods for comparing face recognition algorithms. This document describes Version 5.0 the Colorado State University (CSU) Face Identification Evaluation System. The system includes standardized image pre-processing software, four distinct face recognition algorithms, analysis software to study algorithm performance, and Unix shell scripts to run standard experiments. All code is written in ANSII C. The pre- processing code replicates preprocessing used in the FERET evaluations. The four algorithms provided are Principle Components Analysis (PCA), a.k.a Eigenfaces, a combined Principle Components Analysis and Lin- ear Discriminant Analysis algorithm (PCA+LDA), a Bayesian Intrapersonal/Extrapersonal Classifier (BIC), and an Elastic Bunch Graph Matching (EBGM) algorithm. The PCA+LDA, BIC, and EBGM algorithms are based upon algorithms used in the FERET study contributed by the University of Maryland, MIT, and USC respectively. Two different analysis programs are included in the evaluation system. The first takes as input a set of probe images, a set of gallery images, and similarity matrix produced by one of the four algorithms. It generates a Cumulative Match Curve that plots recognition rate as a function of recognition rank. These plots are common in evaluations such as the FERET evaluation and the Face Recognition Vendor Tests. The second analysis tool generates a sample probability distribution for recognition rate at recognition rank 1, 2, etc. It takes as input multiple images per subject, and uses Monte Carlo sampling in the space of possible probe and gallery choices. This procedure will, among other things, add standard error bars to a Cumulative Match Curve. It will also generate a sample probability distribution for the paired difference between recognition rates for two algorithms, providing an excellent basis for testing if one algorithm consistently out-performs another. The CSU Face Identification Evaluation System is available through our website and we hope it will be used by others to rigorously compare novel face identification algorithms to standard algorithms using a common implementation and known comparison techniques.

Elastic Bunch Graph Matching is a face recognition algorithm that is distributed with CSU's Evaluation of Face Recognition Algorithms System. The algorithm is modeled after the Bochum/USC face recognition algorithm used in the FERET evaluation. The algorithm recognizes novel faces by first localizing a set of landmark features and then measuring similarity between these features. Both localization and comparison uses Gabor jets extracted at landmark positions. In localization, jets are extracted from novel images and matched to jets extracted from a set of training/model jets. Similarity between novel images is expressed as function of similarity between localized Gabor jets corresponding to facial landmarks. A study of how accurately a landmark is localized using different displacement estimation methods is presented. The overall performance of the algorithm subject to changes in the number of training/model images, choice of specific wavelet encoding, displacement estimation technique and Gabor jet similarity measure is explored in a series of independent tests. Several findings were particularly striking, including results suggesting that landmark localization is less reliable than might be expected. However, it is also striking that this did not appear to greatly degrade recognition performance.

Kourtzi and Kanwisher identify regions in the lateral occipital cortex (LOC) with cells that respond to object type, regardless of whether the data is presented as a gray-scale image or a line drawing. They conclude from this data that these regions process or represent structural shape information. This paper suggests a slightly less restrictive explanation: they have identified regions in the LOC that are computationally down stream from complex cells in area V1.

The CSU Face Identification Evaluation System provides standard face recognition algorithms and standard statistical methods for comparing face recognition algorithms. This document describes Version 4.0 the Col- orado State University (CSU) Face Identification Evaluation System. The system includes standardized image pre-processing software, three distinct face recognition algorithms, analysis software to study algorithm perfor- mance, and Unix shell scripts to run standard experiments. All code is written in ANSI C. The preprocessing code replicates feature of preprocessing used in the FERET evaluations. The three algorithms provided are Principle Components Analysis (PCA), a.k.a Eigenfaces, a combined Principle Components Analysis and Lin- ear Discriminant Analysis algorithm (PCA+LDA), and a Bayesian Intrapersonal/Extrapersonal Classifier (BIC). The PCA+LDA and BIC algorithms are based upon algorithms used in the FERET study contributed by the University of Maryland and MIT respectively. Two different analysis programs are included in the evaluation system. The first takes as input a set of probe images, a set of gallery images, and similarity matrix produced by one of the three algorithms. It generates a Cumulative Match Curve that plots recognition rate as a function of recognition rank. These plots are common in evaluations such as the FERET evaluation and the Face Recog- nition Vendor Tests. The second analysis tool generates a sample probability distribution for recognition rate at recognition rank 1, 2, etc. It takes as input multiple images per subject, and uses Monte Carlo sampling in the space of possible probe and gallery choices. This procedure will, among other things, add standard error bars to a Cumulative Match Curve. The CSU Face Identification Evaluation System is available through our website and we hope it will be used by others to rigorously compare novel face identification algorithms to standard algorithms using a common implementation and known comparison techniques.

Various microstructural mechanisms have been suggested for ignition in explosives subjected to impact by low-velocity projectiles. In this study, the effects of shear on the microstructure of PBX 9501 are described. The pseudo two-dimensional, shear-impact experiment, previously employed by Asay, et al. to dynamically study strain localization, is engaged to create shear damage. Impact is achieved by utilizing a gas gun projectile to drive a plunger, which is in contact with the explosive. Post-test microstructural analysis corroborates the observations of other researchers using different diagnostics. Observed features include evidence of shear displacement, the formation of a wedge structure, and reaction in open cracks emanating from the high shear region of the sample. This study also contributes insights concerning the behavior of HMX particles subjected to shear stress. {\copyright}2000 American Institute of Physics.

Sort by:	Author:	Search:
	Keyword:
	Year:

2009

2007

2005

2004

2003

2002

2000