Study on Different Representation Methods for Subspace Segmentation

다국어 초록 (Multilingual Abstract)

With many engineering and science application problems, we must deal with a lot of high-dimensional data, such as videos, images, web documents, text, etc. In the areas of computer vision, image processing and machine learning, high-dimensional data are widespread. However, it is very hard for obtaining meaningful learning and inference from these high-dimensional data directly, the computational complexity of high-dimensional data is often exponential. However, under many conditions, high-dimensional data lie in low-dimensional data corresponding to some classes of the data. Thus, finding the low-dimensional structure from the high-dimensional data is very important. The aim of subspace segmentation is to cluster data that lie in a union of low-dimensional subspaces. In recent years, based on the research of representation methods, many subspace segmentation algorithms appeared. Although these methods are all effective for handling subspace segmentation problems, they all have advantages and disadvantages. This paper focuses on the performance comparison of different subspace segmentation algorithms currently used in handling subspace segmentation problems and views other conventional methods that can be applied in this field.

목차 (Table of Contents)

• Abstract
• 1. Introduction
• 2. Sparse Subspace Clustering (SSC) Method
• 2.1. Problem Formulation
• 2.2. The Steps of SSC Method
• 3. The Extensive Method of SSC
• 4. Low Rank Representation (LRR) methods
• 4.1. Problem Formulation
• 4.2. Under the Conditions that the Data Vectors are Noisy
• 5. Other Improvement Methods based on LRR
• 5.1 Robust Shape Interaction (RSI) Method
• 5.2 Least Squares Regression (LSR) Method
• 5.3 Other Closed form Solution Method based on LRR
• 6. Experiments
• 7. The Comparison of Different Methods
• 8. Conclusions
• Acknowledgements
• References