A New Framework for Balancing Deformability and Discriminability in Computer Vision


Investigator:
Haibin Ling, PhD
Center for Data Analytics and Biomedical Informatics
Dept. of Computer & Information Sciences
Temple University
hbling AT temple.edu
(tel)1-215-204-6973 | (fax)1-215-204-5082

Supported by:
     
NSF project link
      

Summary:
Deformability and discriminability are often two "conflicting" factors in computer vision problems such as shape matching and object recognition. For example, it has been observed that strong deformation invariant descriptors often suffer from low discriminative powers for category recognition. This project develops a new framework for balancing deformability and discriminability for computer vision tasks. The framework uniformly embeds an object, which can be a 2D shape, a point set, an image, a 3D volume or a surface, in a high dimensional space named aspect space. The embedding parameter is then used to control the degree of deformation insensitivity. Both the theoretic and application sides of the proposed framework are investigated. Based on the framework, the project aims to develop three additional research goals: robust shape matching methods by selecting deformability adaptively, robust point set registration methods by dealing with articulation in the framework, and robust image matching by extracting features in the embedded aspect space. These goals are planned to be evaluated on real applications including silhouette-based foliage data retrieval, 3D marker matching in computer-based physical therapy, and image-based disease screening.

Objectives:
The project aims to bridge the two main problems, handling deformation and improving discriminability, which relate to many subfields inside and outside computer vision. The interdisciplinary applications are expected to generate significant contributions to various fields including biodiversity studies, biomedical study, etc. The research results, including code and data, are made public available through the project website.

Publications and Products
Wavelet Domain Multi-fractal Analysis for Static and Dynamic Texture Classification
H. Ji, X. Yang, H. Ling, and Y. Xu
IEEE Trans. on Image Processing (T-IP), 2012
Context-Driven Moving Vehicle Detection in Wide Area Motion Imagery
X. Shi, H. Ling, E. Blasch, and W. Hu
Int'l Conf. on Pattern Recognition (ICPR), 2012.
PDF
Multiple Kernel Learning for Vehicle Detection in Wide Area Motion Imagery
P. Liang, G. Teodoro, H. Ling, E. Blasch, G. Chen, and L. Bai
International Conference on Information Fusion (FUSION), 2012
PDF
Classifying Covert Photographs
H. Lang and H. Ling
IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Rhode Island, 2012
PDF
Online Robust Image Alignment via Iterative Convex Optimization
Y. Wu, B. Shen, and H. Ling
IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Rhode Island, 2012.
PDF
Learning-based Automatic Breast Tumor Detection and Segmentation in Ultrasound Images
P. Jiang, J. Peng, G. Zhang, E. Cheng, V. Megalooikonomou, and H. Ling
Proc. of IEEE Int'l Symposium on Biomedical Imaging (ISBI), 2012
PDF
Real-time Probabilistic Covariance Tracking with Efficient Model Update
Y. Wu, J. Cheng, J. Wang, H. Lu, J. Wang, H. Ling, E. Blasch, and L. Bai
IEEE Trans. on Image Processing (T-IP), 2012, in press
PDF
Analysis of Facial Images Across Age Progression by Humans
J. Zeng, H. Ling, L.J. Latecki, S. Fitzhugh, and G. Guo
ISRN Machine Vision, 2012
Visual Tracking based on Log-Euclidean Riemannian Sparse Representation
Y. Wu, H. Ling, E. Blasch, L. Bai, and G. Chen.
Int'l Symposium on Visual Computing (ISVC), 2011.
Kernel-based Motion-blurred Target Tracking
Y. Wu, J. Hu, F. Li, E. Cheng, J. Yu, and H. Ling.
Int'l Symposium on Visual Computing (ISVC), 2011.
Scale and Object Aware Image Retargeting for Thumbnail Browsing
J. Sun and H. Ling
IEEE International Conference on Computer Vision (ICCV), Barcelona, Spain, 2011.
PDF (~5M)
Blurred Target Tracking by Blur-driven Tracker
Y. Wu, H. Ling, J. Yu, F. Li, X. Mei, and E. Cheng
IEEE International Conference on Computer Vision (ICCV), Barcelona, Spain, 2011.
PDF (~11M) | TUblur sequences and annotation (~430M) |
Dynamic Texture Classification Using Dynamic Fractal Analysis
Y. Xu, Y. Quan, H. Ling, and H. Ji
IEEE International Conference on Computer Vision (ICCV), Barcelona, Spain, 2011.
PDF
Preservative License Plate De-identification for Privacy Protection
L. Du and H. Ling
Int'l Conf. on Document Analysis and Recognition (ICDAR), Beijing, China, 2011.
PDF
Learning-based vessel segmentation in mammographic images
E. Cheng, Shawn McLaughlin, V. Megalooikonomou, P. R. Bakic, A. Maidment, and H. Ling
IEEE Int'l Conf. on Healthcare Informatics, Imaging and Systems Biology (HISB), 2011.
PDF
Robust Visual Tracking and Vehicle Classification via Sparse Representation
Xue Mei and Haibin Ling
IEEE Trans. on Pattern Analysis and Machine Intelligence (PAMI), 2011, in press
PDF | Code |
Multiple Source Data Fusion via Sparse Representation for Robust Visual Tracking
Yi Wu, Erik Blasch, Genshe Chen, Li Bai, and Haibin Ling
International Conference on Information Fusion (FUSION), 2011.
PDF
Evaluation of Visual Tracking in Extremely Low Frame Rate Wide Area Motion Imagery
Haibin Ling, Yi Wu, Erik Blasch, Genshe Chen, Haitao Lang, and Li Bai
International Conference on Information Fusion (FUSION), 2011.
PDF
Minimum Error Bounded Efficient L1 Tracker with Occlusion Detection
Xue Mei, Haibin Ling, Yi Wu, Erik Blasch, and Li Bai
IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Colorado Springs, 2011.
PDF | Data (sequences and annotation, ~190M) |
Illumination Recovery from Image with Cast Shadows via Sparse Representation
Xue Mei, Haibin Ling, and David W. Jacobs
IEEE Trans. on Image Processing (T-IP), 2011, in press
PDF
Balancing Deformability and Discriminability for Shape Matching
Haibin Ling, Xingwei Yang, and Longin Jan Latecki
In Proc. of European Conference on Computer Vision (ECCV), Crete Greece, 2010.
PDF
Efficient Marker Matching Using Pair-wise Constraints in Physical Therapy
Gregory Johnson, Nianhua Xie, Jill Slaboda, Justin Y. Shi, Emily Keshner, and Haibin Ling.
5th Int. Symposium on Visual Computing (ISVC), 2010.
PDF
Category Classification Using Occluding Contours
Jin Sun, Christopher Thorpe, Nianhua Xie, Jingyi Yu, and Haibin Ling
5th Int. Symposium on Visual Computing (ISVC), 2010.
PDF | DT-OC5 dataset