Dimensionality reduction for AI based hyperspectral image classification based on XAI

Vladimir Zeljković; Branka Stojanović; Harald Ganster; Aleksandar Nešković

cs.CVSep 16, 2026

Dimensionality reduction for AI based hyperspectral image classification based on XAI

Authors: Vladimir Zeljković, Branka Stojanović, Harald Ganster, Aleksandar Nešković

Organizations: University of Belgrade School of Electrical Engineering · JOANNEUM RESEARCH Forschungsgesellschaft mbH

Abstract

This research addresses the challenge of limited material recycling in wood recycling processes by leveraging artificial intelligence (AI)-based dimensionality reduction. Our study explores the application of convolutional neural networks (CNNs) in multi-channel hyperspectral imaging (HSI), extending beyond RGB channels to over 200 spectral channels. Dimensionality reduction within this context involves streamlining the feature space for AI system training and inference. Focusing on explainable AI (XAI) methods, this paper contributes to a broader research initiative, presenting a solution framework that enhances the sustainability and efficiency of wood recycling processes.

Figures & tables

Panel of Figure 1 — Figure 1: Averaged heatmaps for different data classes.

Panel of Figure 2 — Figure 2: Visual Comparison of Material Classification Results

Class	One Important Wavelength	Four Important Wavelengths	All Wavelengths
Paper	98.35%	99.84%	99.28%
Plastic	38.94%	74.49%	82.71%
Wood	94.58%	96.10%	95.47%
Background	96.60%	96.77%	96.94%
Glass	97.74%	91.99%	97.35%
Inert	84.83%	89.14%	80.24%

Table 1: Accuracy of Material Classification Using Different Wavelength Sets

Explore similar work

Dimensionality Reduction for Hyperspectral Image Classification
Sep 9, 2026Mohamed Cherifi, Ammar Mesloub, Mohammed Nabil El Korso +2Dimensionality Reduction Hyperspectral Image Classification
Laboratoire Traitement du Signal Ecole Militaire Polytechnique Bordj-El-Bahri, Alger, 16111, Alg´erie · Laboratoire Antennes et Dispositifs Micro-Ondes Ecole Militaire Polytechnique Bordj-El-Bahri, Alger, 16111, Alg´erie · Universit´e Paris-Saclay Saclay, France +1
MixerCA: An Efficient and Accurate Model for High-Performance Hyperspectral Image Classification
Apr 28, 2026Mohammed Q. Alkhatib, Ali JamaliHyperspectral Imaging Efficient Attention
aCollege of Engineering and IT, University of Dubai, Dubai, 14143, UAE · bDepartment of Geography, Simon Fraser University, 8888 University Dr, Burnaby, BC V5A 1S6, Canada
Convolution-Free Holistic Multivariance Decomposition Layer for Efficient Hyperspectral Image Classification Tensor Networks
Aug 17, 2026Süha Tuna, Ülker BaşarHyperspectral Image Classification Hyperspectral Imaging
Istanbul Technical University, Informatics Institute, Maslak 34469, İstanbul, Türkiye · Istanbul Esenyurt University, Faculty of Business and Management Sciences, Department of Management Information Systems, Esenyurt, 34517, İstanbul, Türkiye

Sep 9, 2026J/K move · Enter open · S save

Dimensionality Reduction for Hyperspectral Image Classification

Mohamed Cherifi, Ammar Mesloub, Mohammed Nabil El Korso, Tayeb Touhami+1

Laboratoire Traitement du Signal Ecole Militaire Polytechnique Bordj-El-Bahri, Alger, 16111, Alg´erie · Laboratoire Antennes et Dispositifs Micro-Ondes Ecole Militaire Polytechnique Bordj-El-Bahri, Alger, 16111, Alg´erie · Universit´e Paris-Saclay Saclay, France+1

Dimensionality Reduction Hyperspectral Image Classification

Open paper AskPDF arXiv

This paper addresses the issue of supervised classification in the context of hyperspectral satellite images. It deals with two fundamental aspects: dimensionality reduction of data and the selection of appropriate supervised classification techniques. Firstly, we delve into dimensionality reduction, a critical step in simplifying the management of hyperspectral data. The reduction aims to decrease complexity in terms of memory and computing time. We examine two commonly used methods: Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA). Subsequently, we explore the selection of the most suitable supervised classification algorithms for hyperspectral images. We compare the performance of three methods: K-Nearest Neighbors (KNN), Support Vector Machines (SVM), and Random Forest (RF) using real hyperspectral data. The results highlight that the combination of PCA and RF yields the highest overall accuracy and Kappa coefficient.

Abstract

Explore similar work

Dimensionality Reduction for Hyperspectral Image Classification

MixerCA: An Efficient and Accurate Model for High-Performance Hyperspectral Image Classification

Convolution-Free Holistic Multivariance Decomposition Layer for Efficient Hyperspectral Image Classification Tensor Networks