Next Article in Journal
Quaternion Entropy for Analysis of Gait Data
Next Article in Special Issue
Reconstruction of PET Images Using Cross-Entropy and Field of Experts
Previous Article in Journal
Dynamical and Coupling Structure of Pulse-Coupled Networks in Maximum Entropy Analysis
Previous Article in Special Issue
An Image Encryption Algorithm Based on Time-Delay and Random Insertion
Article

Uncertainty Assessment of Hyperspectral Image Classification: Deep Learning vs. Random Forest

1
Discipline of Geography and Spatial Sciences, School of Technology, Environments and Design, University of Tasmania, Hobart 7018, Australia
2
Centre for Integrative Ecology, School of Life and Environmental Sciences, Deakin University, Burwood 3125, Australia
*
Author to whom correspondence should be addressed.
Entropy 2019, 21(1), 78; https://doi.org/10.3390/e21010078
Received: 16 December 2018 / Revised: 10 January 2019 / Accepted: 10 January 2019 / Published: 16 January 2019
(This article belongs to the Special Issue Entropy in Image Analysis)
Uncertainty assessment techniques have been extensively applied as an estimate of accuracy to compensate for weaknesses with traditional approaches. Traditional approaches to mapping accuracy assessment have been based on a confusion matrix, and hence are not only dependent on the availability of test data but also incapable of capturing the spatial variation in classification error. Here, we apply and compare two uncertainty assessment techniques that do not rely on test data availability and enable the spatial characterisation of classification accuracy before the validation phase, promoting the assessment of error propagation within the classified imagery products. We compared the performance of emerging deep neural network (DNN) with the popular random forest (RF) technique. Uncertainty assessment was implemented by calculating the Shannon entropy of class probabilities predicted by DNN and RF for every pixel. The classification uncertainties of DNN and RF were quantified for two different hyperspectral image datasets—Salinas and Indian Pines. We then compared the uncertainty against the classification accuracy of the techniques represented by a modified root mean square error (RMSE). The results indicate that considering modified RMSE values for various sample sizes of both datasets, the derived entropy based on the DNN algorithm is a better estimate of classification accuracy and hence provides a superior uncertainty estimate at the pixel level. View Full-Text
Keywords: uncertainty assessment; deep neural network; random forest; Shannon entropy uncertainty assessment; deep neural network; random forest; Shannon entropy
Show Figures

Figure 1

MDPI and ACS Style

Shadman Roodposhti, M.; Aryal, J.; Lucieer, A.; Bryan, B.A. Uncertainty Assessment of Hyperspectral Image Classification: Deep Learning vs. Random Forest. Entropy 2019, 21, 78. https://doi.org/10.3390/e21010078

AMA Style

Shadman Roodposhti M, Aryal J, Lucieer A, Bryan BA. Uncertainty Assessment of Hyperspectral Image Classification: Deep Learning vs. Random Forest. Entropy. 2019; 21(1):78. https://doi.org/10.3390/e21010078

Chicago/Turabian Style

Shadman Roodposhti, Majid; Aryal, Jagannath; Lucieer, Arko; Bryan, Brett A. 2019. "Uncertainty Assessment of Hyperspectral Image Classification: Deep Learning vs. Random Forest" Entropy 21, no. 1: 78. https://doi.org/10.3390/e21010078

Find Other Styles
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