Next Article in Journal
Comparison of Hyperspectral Versus Traditional Field Measurements of Fractional Ground Cover in the Australian Arid Zone
Previous Article in Journal
A Composite Method for Predicting Local Accuracies in Remotely Sensed Land-Cover Change Using Largely Non-Collocated Sample Data
Open AccessArticle

Kernel Entropy Component Analysis-Based Robust Hyperspectral Image Supervised Classification

by Bing Tu 1, Chengle Zhou 1,†, Jin Peng 1, Wei He 1,*, Xianfeng Ou 1 and Zhi Xu 2
1
School of Information Science and Technology, Hunan Institute of Science and Technology, Yueyang 414000, China
2
Guangxi Key Laboratory of Images and Graphics Intelligent Processing, Guilin University of Electronics Technology, Guilin 541000, China
*
Author to whom correspondence should be addressed.
Chengle Zhou is the co-first author.
Remote Sens. 2019, 11(23), 2823; https://doi.org/10.3390/rs11232823
Received: 30 October 2019 / Revised: 20 November 2019 / Accepted: 25 November 2019 / Published: 28 November 2019
Recently, the “noisy label" problem has become a hot topic in supervised classification of hyperspectral images (HSI). Nonetheless, how to effectively remove noisy labels from a training set with mislabeled samples is a nontrivial task for a multitude of supervised classification methods in HSI processing. This paper is the first to propose a kernel entropy component analysis (KECA)-based method for noisy label detection that can remove noisy labels of a training set with mislabeled samples and improve performance of supervised classification in HSI, which consists of the following steps. First, the kernel matrix of training samples with noisy labels for each class can be achieved by exploiting a nonlinear mapping function to enlarge the sample separability. Then, the eigenvectors and eigenvalues of the kernel matrix can be obtained by employing symmetric matrix decomposition. Next, the entropy corresponding to each training sample in each class is calculated based on entropy component analysis using the eigenvalues arranged in descending order and the corresponding eigenvectors. Finally, the sigmoid function is applied to the entropy of each sample to obtain the probability distribution. Meanwhile, a decision probability threshold is introduced into the above probability distribution to cleanse the noisy labels of training samples with mislabeled samples for each class. The effectiveness of the proposed method is evaluated by support vector machines on several real hyperspectral data sets. The experimental results show that the proposed KECA method is more efficient than other noisy label detection methods in terms of improving performance of the supervised classification of HSI. View Full-Text
Keywords: kernel trick; entropy component analysis; noisy label; hyperspectral image (HSI); supervised classification; support vector machines (SVMs) kernel trick; entropy component analysis; noisy label; hyperspectral image (HSI); supervised classification; support vector machines (SVMs)
Show Figures

Figure 1

MDPI and ACS Style

Tu, B.; Zhou, C.; Peng, J.; He, W.; Ou, X.; Xu, Z. Kernel Entropy Component Analysis-Based Robust Hyperspectral Image Supervised Classification. Remote Sens. 2019, 11, 2823.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop