Title :
Joint Collaborative Representation With Multitask Learning for Hyperspectral Image Classification
Author :
Jiayi Li ; Hongyan Zhang ; Liangpei Zhang ; Xin Huang ; Lefei Zhang
Author_Institution :
State Key Lab. of Inf. Eng. in Surveying, Mapping, & Remote Sensing, Wuhan Univ., Wuhan, China
Abstract :
In this paper, we propose a joint collaborative representation (CR) classification method with multitask learning for hyperspectral imagery. The proposed approach consists of the following aspects. First, several complementary features are extracted from the hyperspectral image. We next apply these features into the unified multitask-learning-based CR framework to acquire a representation vector and adaptive weight for each feature. Finally, the contextual neighborhood information of the image is incorporated into each feature to further improve the classification performance. The experimental results suggest that the proposed algorithm obtains a competitive performance and outperforms other state-of-the-art regression-based classifiers and the classical support vector machine classifier.
Keywords :
hyperspectral imaging; image classification; learning (artificial intelligence); adaptive weight; hyperspectral image classification; joint collaborative representation classification method; multitask learning; representation vector; support vector machine classifier; Dictionaries; Feature extraction; Hyperspectral imaging; Joints; Training; Vectors; Classification; hyperspectral imagery (HSI); joint collaborative representation (CR) model; multitask learning; sparse representation;
Journal_Title :
Geoscience and Remote Sensing, IEEE Transactions on
DOI :
10.1109/TGRS.2013.2293732