Hyperspectral image classification via contextual deep learning

• Published in: EURASIP journal on image and video processing Vol. 2015; no. 1; pp. 1 - 12
• Main Authors: Ma, Xiaorui, Geng, Jie, Wang, Hongyu
• Format: Journal Article
• Language: English
• Published: Cham Springer International Publishing 14.07.2015; Springer Nature B.V
• Subjects: Algorithms; Biometrics; Classification; Engineering; Feature extraction; Image classification; Image Processing and Computer Vision; Large Scale Learning for Media Understanding; Learning; Pattern Recognition; Pixels; Signal,Image and Speech Processing; Spectra; Strategy; Multinomial logistic regression (MLR); Contextual deep learning; Supervised classification; Hyperspectral image classification
• ISSN: 1687-5281; 1687-5176; 1687-5281
• DOI: 10.1186/s13640-015-0071-8

Because the reliability of feature for every pixel determines the accuracy of classification, it is important to design a specialized feature mining algorithm for hyperspectral image classification. We propose a feature learning algorithm, contextual deep learning, which is extremely effective for hyperspectral image classification. On the one hand, the learning-based feature extraction algorithm can characterize information better than the pre-defined feature extraction algorithm. On the other hand, spatial contextual information is effective for hyperspectral image classification. Contextual deep learning explicitly learns spectral and spatial features via a deep learning architecture and promotes the feature extractor using a supervised fine-tune strategy. Extensive experiments show that the proposed contextual deep learning algorithm is an excellent feature learning algorithm and can achieve good performance with only a simple classifier.