Aleix M. Martinez

Robot Vision Lab
School of Electrical & Computer Engineering
Purdue University, West Lafayette, Indiana

1285 EE Building
Purdue University
West Lafayette, IN 47907-1285

e-mail: aleix@ecn.purdue.edu

New Address:

Aleix M. Martinez is an Assistant Professor at The Ohio State University. He has previously been affiliated to the Electrical and Computer Engineering Department at Purdue University and to the Sony Computer Science Lab. Aleix has worked in projects related to computer vision, pattern recognition, computational neuroscience, computational linguistics, machine learning, robotics, and autonomous agents and is the author of several papers along these lines. He is the author (with Benavente) of the AR-face database. He serves as a referee for several journals (e.g. PAMI, CVIU, TNN) and conferences related to the above areas. Aleix is a co-guest editor (with Kriegman and Yang) of an upcoming special issue on face recognition in the journal Computer Vision and Image Understanding.

CVIU Special Issue on Face Recognition

Some of my projects

Automatic Recognition of American Sign Language: We are currently working on algorithms that can be used to analyze and model ASL. Future work will focus on how to automatically recognize the language and translate it to English. You might be interested to see or obtain the Purdue ASL database .

Face Recognition: Work includes methods to detect and identify faces, with special interest to learning form small training sets. You might be interested to see or obtain my face database (it's publicly available and contains more than 4,000 color images).

Object-Related Image Retrieval: CBIR systems of the future are supposed to facilitates the user's task as much as possible. One such approach is the use of semantics (rather than using a set of low-level features). We present a new approach to semantic access of a database of images by asking for the presence of certain objects; this is known as object-related image retrieval.

ATLAS: This is surely one of the cheapest hexapods ever build (we spend less than $250 on it). MPEG Example [Size ~510k]

NAT and NAT2: These are the two newest robots I have built. Both of them are vision-guided robots able to navigate in a previous unknown environment. AVI Navigation example [Size 4.1M]

Some of my publications

Journals

Recognizing Imprecisely Localized, Partially Occluded and Expression Variant Faces from a Single Sample per Class

A.M. Martinez.
IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 24, No. 6, pp. 748-763, 2002

Abstract   Acrobat   Postscript.Z

Clustering in Image Space for Place Recognition and Visual Annotations for Human-robot Interaction

A.M. Martinez and J. Vitria.
IEEE Transactions on System Man and Cybernetics B, Vol. 31, No. 5, pp. 669-682, 2001

Abstract   Acrobat   Postscript.Z

PCA versus LDA

A.M. Martinez and A.C. Kak.
IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 23, No. 2, pp. 228-233, 2001

Abstract   Acrobat   Postscript.Z

Learning Mixture Models Using a Genetic Version of the EM Algorithm

A.M. Martinez and J. Vitria.
Pattern Recognition Letters 21 (2000) 759-769

Abstract   Acrobat   Postscript.Z

A New Approach to Object-Related Image Retrieval

A.M. Martinez and J.R. Serra.
Journal of Visual Languages and Computing Vol.11, No. 3, pp. 345-363, 2000

Abstract

Conferences

Purdue ASL Database for the Recognition of American Sign Language

A.M. Martinez, R.B. Wilbur, R. Shay and A.C. Kak
Proceedings of IEEE International Conference on Multimodal Interfaces (ICMI), 2002

Acrobat   Postscript

Physical Correlates of Prosodic Structure in American Sign Language

R.B. Wilbur and A.M. Martinez,
Proceedings of the Chicago Linguistics Society (CLS), 2002

Acrobat   Postscript

Recognition of Partially Occluded and/or Imprecisely Localized Faces Using a Probabilistic Approach

A.M. Martinez
Proceedings of IEEE Computer Vision and Pattern Recognition (CVPR), 2000

Abstract   Acrobat   Postscript.Z

Semantic Access of Frontal Face Images: The expression-invariant problem

A.M. Martinez
Proceedings of IEEE Workshop on Content-Based Access of Images and Video Libraries, 2000

Abstract   Acrobat   Postscript.Z

Recognition in Early Visual Attention

A.M. Martinez
Proceedings of European Confrence on Visual Perception (ECVP'99), 1999

Face Image Retrieval Using HMMs

A.M. Martinez
Proceedings of IEEE CVPR'99 (Workshop on Content-Based Access of Images and Video Libraries), 1999

Abstract   Acrobat   Postscript.Z

Semantic Access to a Database of Images: An approach to object-related image retrieval

A.M. Martinez and J.R. Serra.
Proceedings of IEEE Multimedia Systems (ICMCS'99), 1999

Abstract   Acrobat   Postscript.Z

Dimensionality Reduction for Face Recognition

A.M. Martinez and J. Vitria.
In Advances in Visual Form Analysis
C.Arcelli, L.P.Cordella and G.Sanniti (Eds.)
World Scientific, 1997

Abstract

Designing and Implementing Real Walking Agents using Virtual Environments

A.M. Martinez and J. Vitria.
In Applications of Artificial Intelligence (Expert Systems, Robotics and Vision Systems, Fuzzy Logic and Neural Networks)
N.J.Mamede and C. Pinto-Ferreira (Eds.)
Scitec Publications Ltd., 1996

Abstract

A Configurable Massively Parallel Neuroemulator System

Proceedings of the EUROCHIP, 1994

Abstract