Prof. Dr. Longin Jan Latecki

Department of Computer and Information Sciences
Center for Information Science and Technology

Dr. Longin Jan Latecki, Associate Professor

OFFICE : Room 306 Wachman Hall	EMAIL: latecki 'at' temple.edu
ADDRESS: CIS Dept., Temple University Philadelphia, PA 19122, USA	PHONE : (215) 204-5781 FAX : (215) 204-5082

Editorial Board Member	**Pattern Recognition (PR) Journal of Mathematical Imaging and Vision (JMIV)**
Conferences	Int. Workshop on Shape Perception in Human and Computer Vision

Selected Recent Publications

ChengEn Lu, Longin Jan Latecki, Nagesh Adluru, Xingwei Yang, and Haibin Ling. Shape Guided Contour Grouping with Particle Filters. 12th IEEE Int. Conf. on Computer Vision (ICCV), Kyoto, Japan, Sep./Oct. 2009. pdf

Xingwei Yang, Suzan Koknar-Tezel, and Longin Jan Latecki. Locally Constrained Diffusion Process on Locally Densified Distance Spaces with Applications to Shape Retrieval. CVPR 2009. pdf

Xingwei Yang, Longin Jan Latecki, and Dragoljub Pokrajac. Outlier Detection with Globally Optimal Exemplar-Based GMM. SIAM Int. Conf. on Data Mining (SDM09),Sparks, Nevada, April/May, 2009. pdf

Nagesh Adluru and Longin Jan Latecki. Contour Grouping Based on Contour-Skeleton Duality. IJCV 83, pp. 12-29, 2009. pdf

Wenfei Jiang, Longin Jan Latecki, Wenyu Liu, Hui Liang, Ken Gorman. A Video Coding Scheme Based on Joint Spatiotemporal and Adaptive Prediction. IEEE Trans. on Image Processing, Vol. 18, No. 5, 2009. pdf

Longin Jan Latecki, Marc Sobel, Rolf Lakaemper. Piecewise Linear Models with Guaranteed Closeness to the Data. IEEE Trans. PAMI, to appear in 2009. pdf

Longin Jan Latecki, Chengen Lu, Marc Sobel, Xiang Bai. Multiscale Random Fields with Application to Contour Grouping. NIPS 2008. pdf

Complete List of Publications

Awards and Research Grants

Ph. D. Students

Research Goal

Development of intelligent systems for robot perception,
in particular, object detection and recognition in digital images.

Main research topics include:
Shape Based Object Recognition	Skeleton Pruning and Shape Based Image Search Engine
Context Sensitive Shape Retrieval	Results on MPEG-7 CE-Shape-1 Dataset
Geometric Robot Mapping	Demo Videos on Robot Mapping
Video Mining	Video and Vision (ViVi) Lab, Video Summarization
Data Mining	Software for Image Retrieval
Discrete Geometry and Digital Topology	Well-Composed 3D Images