Learning hierarchical dictionary for shape patterns

Authors:
Xiaobing Liu;Bo Zhang
Affiliations:
State Key Laboratory of Intelligent Technology and Systems, Tsinghua National Laboratory for Information Science and Technology, Department of Computer Science and Technology, Tsinghua University, ...;State Key Laboratory of Intelligent Technology and Systems, Tsinghua National Laboratory for Information Science and Technology, Department of Computer Science and Technology, Tsinghua University, ...
Venue:
ISNN'11 Proceedings of the 8th international conference on Advances in neural networks - Volume Part II
Year:
2011

Citing 5
Cited 0

Robust Object Recognition with Cortex-Like Mechanisms

IEEE Transactions on Pattern Analysis and Machine Intelligence
Self-taught learning: transfer learning from unlabeled data

Proceedings of the 24th international conference on Machine learning
Object Class Recognition and Localization Using Sparse Features with Limited Receptive Fields

International Journal of Computer Vision
Sparse shift-invariant NMF

SSIAI '08 Proceedings of the 2008 IEEE Southwest Symposium on Image Analysis and Interpretation
Online dictionary learning for sparse coding

ICML '09 Proceedings of the 26th Annual International Conference on Machine Learning

Quantified Score

Hi-index	0.00

Visualization

Abstract

Shape information is essential for image understanding. Decomposing images into shape patterns using a learned dictionary can provide an effective image representation. However, most of the dictionary based methods retain no structure information between dictionary elements. In this study, We propose Hierarchical Dictionary Shape Decomposition (HiDiShape) to learn a hierarchical dictionary for image shape patterns. Shift Invariant Sparse Coding and HMAX model are combined to decompose image into common shape patterns. And the Sparse Spatial and Hierarchical Regularization (SSHR) is proposed to organize these shape patterns to construct tree structured dictionary. Experiments show that the proposed HiDiShape method can learn tree structured dictionaries for complex shape patterns, and the hierarchical dictionaries improve the performances of corrupted shape reconstruction task.