Next Article in Journal
Cross-Site Scripting Guardian: A Static XSS Detector Based on Data Stream Input-Output Association Mining
Next Article in Special Issue
Multi-mode Microscopic Hyperspectral Imager for the Sensing of Biological Samples
Previous Article in Journal
Design of a Metal 3D Printing Patient-Specific Repairing Thin Implant for Zygomaticomaxillary Complex Bone Fracture Based on Buttress Theory Using Finite Element Analysis
Previous Article in Special Issue
Hyperspectral Imaging for Skin Feature Detection: Advances in Markerless Tracking for Spine Surgery
Open AccessArticle

Multiclass Non-Randomized Spectral–Spatial Active Learning for Hyperspectral Image Classification

1
Advance Image Processing Research Lab (AIPRL), Department of Computer Engineering, Khwaja Fareed University of Engineering and Information Technology, Rahim Yar Khan 64200, Pakistan
2
Dipartimento di Matematica e Informatica—MIFT, University of Messina, 98121 Messina, Italy
3
Institute of Software Development and Engineering, Innopolis University, 420500 Innopolis, Russia
4
Department of Computer Science, Bahauddin Zakariya University, Multan 66000, Pakistan
5
Department of Computer Science, National Textile University, Faisalabad 38000, Pakistan
6
Department of Computer Science, National University of Computer and Emerging Sciences, Islamabad, Chiniot-Faisalabad Campus, Chiniot 35400, Pakistan
7
Machine Learning & Knowledge Representation (MlKr) lab, Institute of Data Science & AI, Innopolis University, 420500 Innopolis, Russia
*
Authors to whom correspondence should be addressed.
Appl. Sci. 2020, 10(14), 4739; https://doi.org/10.3390/app10144739
Received: 7 June 2020 / Revised: 3 July 2020 / Accepted: 6 July 2020 / Published: 9 July 2020
(This article belongs to the Special Issue Hyperspectral Imaging, Methods and Applications)
Active Learning (AL) for Hyperspectral Image Classification (HSIC) has been extensively studied. However, the traditional AL methods do not consider randomness among the existing and new samples. Secondly, very limited AL research has been carried out on joint spectral–spatial information. Thirdly, a minor but still worth mentioning factor is the stopping criteria. Therefore, this study caters to all these issues using a spatial prior Fuzziness concept coupled with Multinomial Logistic Regression via a Splitting and Augmented Lagrangian (MLR-LORSAL) classifier with dual stopping criteria. This work further compares several sample selection methods with the diverse nature of classifiers i.e., probabilistic and non-probabilistic. The sample selection methods include Breaking Ties (BT), Mutual Information (MI) and Modified Breaking Ties (MBT). The comparative classifiers include Support Vector Machine (SVM), Extreme Learning Machine (ELM), K-Nearest Neighbour (KNN) and Ensemble Learning (EL). The experimental results on three benchmark hyperspectral datasets reveal that the proposed pipeline significantly increases the classification accuracy and generalization performance. To further validate the performance, several statistical tests are also considered such as Precision, Recall and F1-Score. View Full-Text
Keywords: Hyperspectral Image Classification (HSIC); Active Learning (AL); Query Function; ELM; KNN; SVM; Multinomial Logistic Regression via Splitting and Augmented Lagrangian (MLR-LORSAL) Hyperspectral Image Classification (HSIC); Active Learning (AL); Query Function; ELM; KNN; SVM; Multinomial Logistic Regression via Splitting and Augmented Lagrangian (MLR-LORSAL)
Show Figures

Figure 1

MDPI and ACS Style

Ahmad, M.; Mazzara, M.; Raza, R.A.; Distefano, S.; Asif, M.; Sarfraz, M.S.; Khan, A.M.; Sohaib, A. Multiclass Non-Randomized Spectral–Spatial Active Learning for Hyperspectral Image Classification. Appl. Sci. 2020, 10, 4739.

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
Search more from Scilit
 
Search
Back to TopTop