A statistical approach to 3d object detection applied to faces and cars
Published 1 January 2000
Henry Schneiderman, Takeo Kanade
Citations245
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
This thesis describes a statistical method for 3D object detection that has developed the first algorithm that can reliably detect faces that vary from frontal view to full profile view and the first algorithms thatCan reliably detect cars over a wide range of viewpoints.
Abstract
In this thesis, we describe a statistical method for 3D object detection. In this method, we decompose the 3D geometry of each object into a small number of viewpoints. For each view-point, we construct a decision rule that determines if the object is present at that specific orienta-tion. Each decision rule uses the statistics of both object appearance and “non-object ” visual appearance. We represent each set of statistics using a product of histograms. Each histogram represents the joint statistics of a subset of wavelet coefficients and their position on the object. Our approach is to use many such histograms representing a wide variety of visual attributes. Using this method, we have developed the first algorithm that can reliably detect faces that vary from frontal view to full profile view and the first algorithm that can reliably detect cars over a wide range of viewpoints. Acknowledgments I would like to thank my advisor, Takeo Kanade, for his guidance in this research. His ideas, insights, suggestions, questions, and enthusiasm were great help in stimulating my thought and in bringing this research forward. I would like to thank the other members of my dissertation com-
Keywords
Computer Science
The Nature of Statistical Learning Theory
39,279 Citations1995Vladimir Vapnik
Machine LearningSupport-Vector Networks
33,035 Citations1995Corinna Cortes, Vladimir Vapnik
High generalization ability of support-vector networks utilizing polynomial input transformations is demonstrated and the performance of the support- vector network is compared to various classical learning algorithms that all took part in a benchmark study of Optical Character Recognition.
Journal of Computer and System SciencesA Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting
20,320 Citations1997Yoav Freund, Robert E. Schapire
Choice Reviews OnlineNeural networks for pattern recognition
18,687 Citations1994
This is the first comprehensive treatment of feed-forward neural networks from the perspective of statistical pattern recognition, and is designed as a text, with over 100 exercises, to benefit anyone involved in the fields of neural computation and pattern recognition.
Journal of the American Statistical AssociationProbability, Random Variables, and Stochastic Processes.
16,350 Citations1984Julia Abrahams, A. Papoulis
Computers in PhysicsTen Lectures on Wavelets
15,386 Citations1992Ingrid Daubechies, Christopher Heil
This paper presents a meta-analyses of the wavelet transforms of Coxeter’s inequality and its applications to multiresolutional analysis and orthonormal bases.
Journal of Cognitive NeuroscienceEigenfaces for Recognition
13,775 Citations1991Matthew Turk, Alex Pentland
A near-real-time computer system that can locate and track a subject's head, and then recognize the person by comparing characteristics of the face to those of known individuals, and that is easy to implement using a neural network architecture.
IEEE Transactions on Pattern Analysis and Machine IntelligenceEigenfaces vs. Fisherfaces: recognition using class specific linear projection
11,753 Citations1997Peter N. Belhumeur, João P. Hespanha +1 more
Good features to track
6,858 Citations1994Jianbo Shi, Tomasi
A feature selection criterion that is optimal by construction because it is based on how the tracker works, and a feature monitoring method that can detect occlusions, disocclusions, and features that do not correspond to points in the world are proposed.
Cambridge University Press eBooksPattern Recognition and Neural Networks
6,468 Citations1996B. D. Ripley
International Journal of Computer VisionColor indexing
5,592 Citations1991Michael J. Swain, Dana H. Ballard
It is demonstrated that color histograms of multicolored objects provide a robust, efficient cue for indexing into a large database of models and that they can differentiate among a large number of objects.
IEEE Transactions on Pattern Analysis and Machine IntelligenceThe FERET evaluation methodology for face-recognition algorithms
4,692 Citations2000P. Jonathon Phillips, Hyeonjoon Moon +2 more
IEEE Transactions on Pattern Analysis and Machine IntelligenceLeast-Squares Fitting of Two 3-D Point Sets
3,930 Citations1987K.S. Arun, Thomas S. Huang +1 more
An algorithm for finding the least-squares solution of R and T, which is based on the singular value decomposition (SVD) of a 3 × 3 matrix, is presented.
IEEE Transactions on Pattern Analysis and Machine IntelligenceNeural network-based face detection
3,521 Citations1998Henry A. Rowley, Shumeet Baluja +1 more
Machine LearningOn the Optimality of the Simple Bayesian Classifier under Zero-One Loss
3,072 Citations1997Pedro Domingos, Michael J. Pazzani
The Bayesian classifier is shown to be optimal for learning conjunctions and disjunctions, even though they violate the independence assumption, and will often outperform more powerful classifiers for common training set sizes and numbers of attributes, even if its bias is a priori much less appropriate to the domain.
Wavelets and Subband Coding
2,913 Citations1995Martin Vetterli, Jelena Kovačević
Wavelets and Subband Coding offered a unified view of the exciting field of wavelets and their discrete-time cousins, filter banks, or subband coding and developed the theory in both continuous and discrete time.
IEEE Transactions on Pattern Analysis and Machine IntelligenceFace recognition by elastic bunch graph matching
2,882 Citations1997Laurenz Wiskott, Jean‐Marc Fellous +2 more
Machine LearningAn Empirical Comparison of Voting Classification Algorithms: Bagging, Boosting, and Variants
2,644 Citations1999Eric Bauer, Ron Kohavi
It is found that Bagging improves when probabilistic estimates in conjunction with no-pruning are used, as well as when the data was backfit, and that Arc-x4 behaves differently than AdaBoost if reweighting is used instead of resampling, indicating a fundamental difference.
Medical Entomology and ZoologyTwo-Dimensional Signal and Image Processing
2,573 Citations1989Jae S. Lim
This text covers the principles and applications of "multidimensional" and "image" digital signal processing and is suitable for Sr/grad level courses in image processing in EE departments.
Training support vector machines: an application to face detection
2,496 Citations2002E. Osuna, Robert M. Freund +1 more
A decomposition algorithm that guarantees global optimality, and can be used to train SVM's over very large data sets is presented, and the feasibility of the approach on a face detection problem that involves a data set of 50,000 data points is demonstrated.
International Journal of Computer VisionVisual learning and recognition of 3-d objects from appearance
1,891 Citations1995Hiroshi Murase, Shree K. Nayar
A near real-time recognition system with 20 complex objects in the database has been developed and a compact representation of object appearance is proposed that is parametrized by pose and illumination.
View-based and modular eigenspaces for face recognition
1,813 Citations1994Pentland, Moghaddam +1 more
A modular eigenspace description technique is used which incorporates salient features such as the eyes, nose and mouth, in an eigenfeature layer, which yields higher recognition rates as well as a more robust framework for face recognition.
IEEE Transactions on ComputersDistortion invariant object recognition in the dynamic link architecture
1,810 Citations1993Martin Lades, Jan C. Vorbrüggen +5 more
An object recognition system based on the dynamic link architecture, an extension to classical artificial neural networks (ANNs), is presented and the implementation on a transputer network achieved recognition of human faces and office objects from gray-level camera images.
Face Recognition by Elastic Bunch Graph Matching*†
1,770 Citations2022Laurenz Wiskott, Jean‐Marc Fellous +2 more
IEEE Transactions on Pattern Analysis and Machine IntelligenceExample-based learning for view-based human face detection
1,769 Citations1998Kah Kay Sung, Tomaso Poggio
An example-based learning approach for locating vertical frontal views of human faces in complex scenes and shows empirically that the distance metric adopted for computing difference feature vectors, and the "nonface" clusters included in the distribution-based model, are both critical for the success of the system.
IEEE Transactions on Pattern Analysis and Machine IntelligenceProbabilistic visual learning for object representation
1,451 Citations1997B. Moghaddam, Alex Pentland
An unsupervised technique for visual learning is presented, which is based on density estimation in high-dimensional spaces using an eigenspace decomposition and is applied to the probabilistic visual modeling, detection, recognition, and coding of human faces and nonrigid objects.
A general framework for object detection
1,430 Citations2002C. Papageorgiou, Michael B. Oren +1 more
A general trainable framework for object detection in static images of cluttered scenes based on a wavelet representation of an object class derived from a statistical analysis of the class instances and a motion-based extension to enhance the performance of the detection algorithm over video sequences is presented.
The Annals of StatisticsArcing classifier (with discussion and a rejoinder by the author)
1,105 Citations1998Leo Breiman
Two arcing algorithms are explored, compared to each other and to bagging, and the definitions of bias and variance for a classifier as components of the test set error are introduced.
MIT Press eBooksGeometric invariance in computer vision
1,022 Citations1992Joseph L. Mundy, Andrew Zisserman
Part 1 foundations: algebraic invariants - invariant theory and enumerative combinatorics of young tableaux, and applications: transformation invariant indexing and invariant linear methods in photogrammetry and model-matching.
Research Showcase @ Carnegie Mellon University (Carnegie Mellon University)Obstacle avoidance and navigation in the real world by a seeing robot rover
857 Citations2018Hans Moravec
The program has successfully driven the cart through several 20 meter indoor courses complex enough to necessitate three or four avoiding swerves, and a less successful outdoor run, in which the cart skirted two obstacles but collided with a third, was also done.
IEEE Transactions on Pattern Analysis and Machine IntelligenceRecognition by linear combinations of models
817 Citations1991Shimon Ullman, Ronen Basri
An approach to visual object recognition in which a 3D object is represented by the linear combination of 2D images of the object is proposed and it is shown that for objects with sharp edges as well as with smooth bounding contours, the set of possible images of a given object is embedded in a linear space spanned by a small number of views.
Geometric Hashing: A General And Efficient Model-based Recognition Scheme
776 Citations2005Y. Lamdan, Haim J. Wolfson
A general method for model-based object recognition in occluded scenes is presented based on geometric hashing, which stands out for its efficiency and applications both in 3-D and 2-D.
Pedestrian detection using wavelet templates
693 Citations2002Michael B. Oren, C. Papageorgiou +3 more
This paper presents a trainable object detection architecture that is applied to detecting people in static images of cluttered scenes and shows how the invariant properties and computational efficiency of the wavelet template make it an effective tool for object detection.
The FERET evaluation methodology for face-recognition algorithms
589 Citations2002P. Jonathon Phillips, Hyeonjoon Moon +2 more
Two of the most critical requirements in support of producing reliable face-recognition systems are a large database of facial images and a testing procedure to evaluate systems.
International Journal of Computer VisionRecognizing solid objects by alignment with an image
531 Citations1990Daniel P. Huttenlocher, Shimon Ullman
A new method for computing a transformation from a three-dimensional model coordinate frame to the two-dimensional image coordinate frame, using three pairs of model and image points, is developed, showing that this transformation always exists for three noncollinear points, and is unique up to a reflective ambiguity.
IEEE Transactions on Pattern Analysis and Machine IntelligenceStructural indexing: efficient 3-D object recognition
490 Citations1992Fridtjof Stein, Gérard Medioni
The approach uses two different types of primitives for matching: small surface patches, where differential properties can be reliably computed, and lines corresponding to depth or orientation discontinuities, which are represented by splashes and 3-D curves, respectively.
Control Engineering PracticeDigital neural networks
478 Citations1994
This chapter discusses the development of unsupervised networks for association/Classification and their applications in neural nets, as well as some of the techniques used in conventional optimization techniques.
IEEE Transactions on Pattern Analysis and Machine IntelligenceInvariant descriptors for 3D object recognition and pose
402 Citations1991David Forsyth, Joseph L. Mundy +4 more
A model-based vision system that recognizes curved plane objects irrespective of their pose is demonstrated and the stability of a range of invariant descriptors to measurement error is treated in detail.
International Journal of Computer VisionRecognition without Correspondence using Multidimensional Receptive Field Histograms
397 Citations2000Bernt Schiele, James L. Crowley
A technique where appearances of objects are represented by the joint statistics of such local neighborhood operators represents a new class of appearance based techniques for computer vision that can identify over 100 objects in the presence of major occlusions.
Applied OpticsTutorial survey of composite filter designs for optical correlators
377 Citations1992B. V. K. Vijaya Kumar
A tutorial survey is presented of the many composite filter designs proposed for distortion-invariant optical pattern recognition and remarks are made regarding areas for further investigation.
Probabilistic visual learning for object detection
360 Citations2002B. Moghaddam, Alex Pentland
An unsupervised technique for visual learning which is based on density estimation in high-dimensional spaces using an eigenspace decomposition and a multivariate Mixture-of-Gaussians model is presented.
Probabilistic modeling of local appearance and spatial relationships for object recognition
356 Citations2002Henry Schneiderman, Takeo Kanade
An algorithm for object recognition that explicitly models and estimated the posterior probability function, P(object/image) in closed form is described, which captures the joint statistics of local appearance and position on the object as well as the statistics ofLocal appearance in the visual world at large.
Lecture notes in computer scienceSemi-naive bayesian classifier
333 Citations1991Igor Kononenko
The algorithm of the 'naive' Bayesian classifier (that assumes the independence of attributes) is extended to detect the dependencies between attributes to optimize the tradeoff between the 'non-naivety' and the reliability of approximations of probabilities.
A SNoW-Based Face Detector
310 Citations1999Ming–Hsuan Yang, Dan Roth +1 more
Experimental results on commonly used benchmark data sets of a wide range of face images show that the SNoW-based approach outperforms methods that use neural networks, Bayesian methods, support vector machines and others.
Machine LearningMaximum Entropy Discrimination
259 Citations2004Tony Jebara
A general framework for discriminative estimation based on the maximum entropy principle and its extensions is presented and preliminary experimental results are indicative of the potential in these techniques.
Pattern Recognition with Neural Networks in C++
235 Citations2021Abhijit S. Pandya, Robert B. Macy
Pattern Recognition with Neural Networks in C++ covers pattern classification and neural network approaches within the same framework and provides an intuitive explanation of each method for each network paradigm.
Face recognition by elastic bunch graph matching
231 Citations1997Laurenz Wiskott, Jean‐Marc Fellous +2 more
A system for recognizing human faces from single images out of a large database containing one image per person, based on a Gabor wavelet transform, which differs from Lades et al. (1993) in three respects.
IEEE Transactions on Image ProcessingVector quantization of image subbands: a survey
179 Citations1996Pamela C. Cosman, Robert M. Gray +1 more
Face detection with information-based maximum discrimination
154 Citations2002Antonio J. Colmenarez, Thomas S. Huang
A visual learning technique that maximizes the discrimination between positive and negative examples in a training set by using a family of discrete Markov processes to model the face and background patterns and estimate the probability models using the data statistics.
IEEE Transactions on Pattern Analysis and Machine IntelligenceEfficiently computing and representing aspect graphs of polyhedral objects
149 Citations1991Z. Gigus, John Canny +1 more
Pattern Recognition LettersArtificial neural networks in real-time car detection and tracking applications
131 Citations1996Christian Goerick, Detlev Noll +1 more
Three applications representing different approaches to car detection and tracking problems are presented, and artificial neural networks are utilized to solve the essential subproblems.
International Journal of Computer VisionStatistical Approaches to Feature-Based Object Recognition
130 Citations1997William M. Wells
Evidence is presented indicating that, in some domains, normal (Gaussian) distributions are more accurate than uniform distributions for modeling feature fluctuations, which motivates the development of new maximum-likelihood and MAP recognition formulations which are based on normal feature models.
IEEE Transactions on Pattern Analysis and Machine IntelligenceSensor modeling, probabilistic hypothesis generation, and robust localization for object recognition
118 Citations1995Mark D. Wheeler, Katsushi Ikeuchi
Philosophical Transactions of the Royal Society A Mathematical Physical and Engineering SciencesWavelets, vision and the statistics of natural scenes
111 Citations1999David J. Field
This paper reviews some of the statistical properties of natural scenes that allow the visual code to be efficient and argues that such wavelet codes are efficient because they increase the independence of the vectors' outputs by finding the sparse structure available in the input.
IEEE Transactions on Pattern Analysis and Machine IntelligenceAre multilayer perceptrons adequate for pattern recognition and verification?
108 Citations1998Marco Gori, Franco Scarselli
It is proven that multilayer perceptrons with sigmoidal units and a number of hidden units less or equal than the number of inputs are unable to model patterns distributed in typical clusters, since these networks draw open separation surfaces in the pattern space.
Recognition of planar object classes
101 Citations1996Michael C. Burl, Pietro Perona
A new framework for recognizing planar object classes is presented, which is based on local feature detectors and a probabilistic model of the spatial arrangement of the features, and the allowed object deformations are represented through shape statistics, which are learned from examples.
Neural NetworksCueing, feature discovery, and one-class learning for synthetic aperture radar automatic target recognition
80 Citations1995Mark W. Koch, Mary M. Moya +2 more
A modular multi-stage architecture for focus-of-attention cueing, feature discovery and extraction, and one-class pattern learning and identification in synthetic aperture radar imagery is described.
Neural Network-Based Face Detection
68 Citations1999Henry A. Rowley
Higher order statistical learning for vehicle detection in images
60 Citations1999A. N. Rajagopalan, Philippe Burlina +1 more
The proposed method approximately models the unknown distribution of the images of vehicles by learning higher order statistics (HOS) information of the 'vehicle class' from sample images by learning 'on the fly' statistical information about the background.
DSpace@MIT (Massachusetts Institute of Technology)A Trainable Object Detection System: Car Detection in Static Images
58 Citations1999C. Papageorgiou, Tomaso Poggio
This paper describes a general, trainable architecture for object detection that has previously been applied to face and people detection with a new application to car detection in static images that uses a set of labeled training data from which an implicit model of an object class { here, cars { is learned.
Neural NetworksClassifier and shift-invariant automatic target recognition neural networks
50 Citations1995David Casasent, Leonard Neiberg
A new feature space trajectory classifier neural network is described that identifies the class and pose of each object, rejects clutter false alarms, and overcomes various issues associated with other classier neural networks.
Detection of human faces using decision trees
46 Citations2002Jeffrey Huang, Srinivas Gutta +1 more
A novel algorithm for face detection using decision trees (DT) is proposed and its generality and feasibility is shown using a database consisting of 2340 face images from the FERET database over a semi-uniform background.
Probabilistic object recognition and localization
40 Citations1999Bernt Schiele, Alex Pentland
A Probabilistic technique based on joint statistics is developed for the identification of multiple objects at arbitrary positions and orientations and by incorporating structural dependencies, a procedure for probabilistic localization of objects is obtained.
A cluster-based statistical model for object detection
40 Citations1999T.D. Rikert, Michael Jones +1 more
This paper presents an approach to object detection which is based on recent work in statistical models for texture synthesis and recognition, and presents promising results in applying the technique to face detection and car detection.
Eigenfeatures for planar pose measurement of partially occluded objects
37 Citations1996John Krumm
This work presents an algorithm that is robust in these terms, which uses several small features on the object rather than a monolithic template, giving the system robustness in the face of background clutter and partial occlusions.
DSpace@MIT (Massachusetts Institute of Technology)Complex Feature Recognition: A Bayesian Approach for Learning to Recognize Objects
23 Citations1996Paul Viola
A new Bayesian framework for visual object recognition which is based on the insight that images of objects can be modeled as a conjunction of local features, and uses a large set of complex features that are learned from experience with model objects.