A4 Article in conference proceedings
Minimal learning machine in hyperspectral imaging classification (2020)

Hakola, A.-M., & Pölönen, I. (2020). Minimal learning machine in hyperspectral imaging classification . In L. Bruzzone, F. Bovolo, & E. Santi (Eds.), Image and Signal Processing for Remote Sensing XXVI (Article 115330R). SPIE. Proceedings of SPIE : the International Society for Optical Engineering, 11533. https://doi.org/10.1117/12.2573578

JYU authors or editors

Publication details

All authors or editors: Hakola, Anna-Maria; Pölönen, Ilkka

Parent publication: Image and Signal Processing for Remote Sensing XXVI

Parent publication editors: Bruzzone, Lorenzo; Bovolo, Francesca; Santi, Emanuele

Place and date of conference: Online, 21.-25.9.2020

ISBN: 978-1-5106-3879-2

eISBN: 978-1-5106-3880-8

Journal or series: Proceedings of SPIE : the International Society for Optical Engineering

ISSN: 0277-786X

eISSN: 1996-756X

Publication year: 2020

Number in series: 11533

Article number: 115330R

Publisher: SPIE

Publication country: United States

Publication language: English

DOI: https://doi.org/10.1117/12.2573578

Publication open access: Not open

Publication channel open access:

Publication is parallel published (JYX): https://jyx.jyu.fi/handle/123456789/72431


A hyperspectral (HS) image is typically a stack of frames, where each frame represents the intensity of a different wavelength of light. Each spatial pixel has a spectrum. In the classification of the HS image, each spectrum is classified pixel-by-pixel. In some of the real-time applications, the amount of the HS image data causes performance challenges. Those issues relate to the platforms (e.g. drones) payload restrictions, the issues of the available energy and to the complexity of the machine learning models. In this study, we introduce the minimal learning machine (MLM) as a computationally cheap training and classification machine learning method for the hyperspectral imaging classification. MLM is a distance-based method that utilizes mapping between input and and output distances. Input distance is a distance between the training set and its subset R. Output distance is corresponding distances between the label values of the training set and the subset R. We propose a training point selection framework, which reduces the number of data points in the R by selecting the points class-by-class, in the direction of the principal components of each class. We test MLM’s performance against four other classification machine learning methods: Random Forest, Artificial Neural Network, Support Vector Machine and Nearest Neighbours classifier with three known hyper- spectral data sets. As the main outcomes, we will show how the performance is affected by the size of the subset R. We compare our subset selection method MLM’s performance to the random selection MLM’s perfor- mance. Results show that MLM is an computationally efficient way to train large training sets. MLM reduces the complexity of the analysis and provides computational benefits against other models. Proposed framework offers tools that can improve the MLM’s classification time and the accuracy rate compared to the MLM with randomly picked training points.

Keywords: spectral imaging; imaging; machine learning

Free keywords: Hyperspectral Imaging; Minimal Learning Machine; Classification; Principal Component Analysis; Distance Learning

Contributing organizations

Related projects

Ministry reporting: Yes

Reporting Year: 2020

JUFO rating: 0

Last updated on 2021-16-07 at 10:45