CSE 902: Selected Topics in Recognition by Machine

Theme for spring, 2003: Computer Vision and Pattern Recognition in Practice

Instructor: Anil Jain: Office: 3145 Engineering Building; Phone: 355-9282; E-mail: jain at cse.msu.edu; Office Hours: MW 9-10 or by appointment.
Class: 3:00pm - 4:20pm, Tuesdays and Thursdays, room 1314EB.
Text: Readings from journals.
Prerequisites: CSE 802 and CSE 803.

Description

This course is designed for graduate students who plan to pursue their thesis research in the general area of computer vision and pattern recognition. Students in the class are expected to have basic understanding of classifier design and image analysis as covered in CSE 802 and CSE 803. The main objective of the course is to provide students an in-depth knowledge of some of the current research topics in these areas. Students will attain this through a "hands on" project involving real data and images and through reading papers published in the current literature. A quick glance at the 12 issues of the IEEE Trans. PAMI published in 2002 indicates that a majority of the papers covered one of the following topics: pattern classification and feature selection; clustering and data mining; face recognition and biometrics; motion tracking; segmentation and feature extraction; shape extraction and matching; robot vision and navigation; handwriting and document analysis; and texture. Our coverage of the topics in this course will reflect this trend in the current literature. Of course, student interest will also be taken in to consideration in determining the hands-on projects.

Topics

Projection of multidimensional data and dimensionality reduction
Data clustering and unsupervised learning
Fingerprint image restoration
Face detection, recognition and tracking
Content-based image retrieval
Integrated segmentation & classification of vehicle occupants
On-line/off-line document segmentation
Forensic dentistry

Grading:

Students will work in teams of 3-4 students on a specific "hands on" project. Each student will present background papers and results of the project in the class. There will be no exams in the course. Grades will be assigned based on classroom participation, quality of presentation, interim project report (middle of the semester) and the final project report.

Resources

Nonlinear Dimensionality Reduction and Manifold Learning. [PPT Slides]
Fingerprint Image Enhancement. [PDF Slides]
Kevin Murphy, A Brief Introduction to Graphical Models and Bayesian Networks. [HTML Document]
E. Charniak, 1991. "Bayesian Networks without Tears", AI magazine. [PDF]
Ana L.N. Fred and Anil K. Jain, "Evidence Accumulation Clustering based on the K-means algorithgm", Proc. Structural and Syntactic Pattern Recognition (SSPR), Windsor, Canada, August 2002.
Ana L.N. Fred and Anil K. Jain, "Data Clustering Using Evidence Accumulation", Proc. International Conference on Pattern Recognition (ICPR), Quebec City, August 2002.
Daniel Lopresti and Andrew Tomkins, "On the Searchability Of Electronic Ink".
S. Basu, A. Banerjee and R. Mooney, "Semi-supervised Clustering by Seeding", Proc. of the 19th Int'l Conf on Machine Learning, pp. 19-26, Sydney, July 2002.
A. Hyvarinen and E. Oja, "Independent component analysis: algorithms and applications", Neural Networks, pp. 411-430, 2000.
S. Periaswamy and H. Farid, "Elastic Registration in the Presence of Intensity Variations", to appear in: IEEE Transactions on Medical Imaging.
J. Shi and J. Malik. "Normalized Cuts and Image Segmentation". IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 22 (8), pp. 888 -- 905, August 2002.
A. Ng, M. Jordan, and Y. Weiss. "On spectral clustering: Analysis and an algorithm". In Advances in Neural Information Processing Systems 14: Proceedings of the 2001.
W. Hwang and J. Wang, "Hierarchical Discriminant Regression", IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 22, no. 11, November 2000, pp. 1277-1293.
M. Skurichina and R.P.W. Duin, "Bagging, Boosting and the Random Subspace Method for Linear Classifiers", Pattern Analysis and Applications, (2002)5:121-135.
J. Kittler, M. Hatef, R.P.W. Duin and J. Matas, "On Combining Classifiers", IEEE Transactions on PAMI, vol. 20, no. 3, March 1998.
B. J. Frey and N. Jojic, "Transformation-Invariant Clustering and Dimensionality Reduction Using EM", To appear in IEEE Trans. on PAMI
M. Belkin and P. Niyogi, "Laplacian Eigenmaps and Spectral Techniques for Embedding and Clustering", NIPS, 2001.
M. Belkin and P. Niyogi, "Using Manifold Structure for Partially Labelled Classification", NIPS, 2002.
Hieu Tat Nguyen, Marcel Worring, and Rein van den Boomgaard, "Watersnakes: Energy-Driven Watershed Segmentation", IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 25, No. 3, March 2003, pp. 330-342.
K. Nigam et al., "Text Classification from Labeled and Unlabeled Documents Using EM", Machine Learning, 1-34, 1999.
L. Vincent and P. Soille, "Watersheds in Digital Spaces: An Efficient Algorithm Based on Immersion Simulations", IEEE Transactions on PAMI, Vol. 13, No. 6, June 1991, pp. 583-598.
D. Comaniciu and P. Meer, "Mean shift: A robust approach toward feature space analysis", IEEE Transactions PAMI, Vol. 24, No. 5, May 2002, pp. 603-619.
Yizong Cheng, "Mean shift, Mode Seeking, and Clustering", IEEE Transactions on PAMI, Vol. 17, No. 8, August 1995, pp. 790-799. ( abstract )
Code & Software for Mean Shift
G.D. Tourassi, E.D. Frederick, M.K. Markey and C.E. Floyd, Jr., "Application of the mutual information criterion for feature selection in computer-aided diagnosis", Med. Phys., (28)12, December 2001, pp. 2394-2402. [PPT Slides]
J.P.W. Pluim, J.B.A. Maintz and M.A. Viergever, "Mutual information based registration of medical images: a survey", to appear in IEEE Trans. Medical Imaging, 2003.
M.D. Esteban and D. Morales, "A Summary on Entropy Statistics".