Recursive autoencoders based unsupervised feature learning for hyperspectral image classification

Xiangrong Zhang, Yanjie Liang, Chen Li, Licheng Jiao, Huiyu Zhou

Research output: Contribution to journalArticlepeer-review

33 Citations (Scopus)
684 Downloads (Pure)


For hyperspectral image (HSI) classification, it is very important to learn effective features for the discrimination purpose. Meanwhile, the ability to combine spectral and spatial information together in a deep level is also important for feature learning. In this letter, we propose an unsupervised feature learning method for HSI classification, which is based on recursive autoencoders (RAE) network. RAE utilizes the spatial and spectral information and produces high-level features from the original data. It learns features from the neighborhood of the investigated pixel to represent the whole local homogeneous area of the image. In addition, to obtain more accurate representation of the investigated pixel, a weighting scheme is adopted based on the neighboring pixels, where the weights are determined by the spectral similarity between the neighboring pixels and the investigated pixel. The effectiveness of our method is evaluated by the experiments on two hyperspectral datasets and the results show that our proposed method has better performance.
Original languageEnglish
Number of pages5
JournalIEEE Geoscience and Remote Sensing Letters
Early online date11 Oct 2017
Publication statusEarly online date - 11 Oct 2017


Dive into the research topics of 'Recursive autoencoders based unsupervised feature learning for hyperspectral image classification'. Together they form a unique fingerprint.

Cite this