FCM Approach of Similarity and Dissimilarity Measures with α-Cut for Handling Mixed Pixels

Sayan Mukhopadhaya,Alfred Stein,Anil Kumar

doi:10.3390/rs10111707

Sayan Mukhopadhaya, Alfred Stein + Show 1 more

Open Access

https://doi.org/10.3390/rs10111707

Copy DOI

Journal: Remote sensing	Publication Date: Oct 29, 2018
Citations: 5	License type: CC BY 4.0

Affiliation: Indian Institute of Remote Sensing

Abstract

In this paper, the fuzzy c-means (FCM) classifier has been studied with 12 similarity and dissimilarity measures: Manhattan distance, chessboard distance, Bray–Curtis distance, Canberra, Cosine distance, correlation distance, mean absolute difference, median absolute difference, Euclidean, Mahalanobis, diagonal Mahalanobis and normalised squared Euclidean distance. Both single and composite modes were used with a varying weight constant (m*) and also at different α-cuts. The two best single measures obtained were combined to study the effect of composite measures on the datasets used. An image-to-image accuracy check was conducted to assess the accuracy of the classified images. Fuzzy error matrix (FERM) was applied to measure the accuracy assessment outcomes for a Landsat-8 dataset with respect to the Formosat-2 dataset. To conclude, FCM classifier with Cosine measure performed better than the conventional Euclidean measure. But, due to the incapability of the FCM classifier to handle noise properly, the classification accuracy was around 75%.

Highlights

Remote-sensing image data are classified to generate user-defined labels [1]
The optimization of the parameter value of weighed constant (m∗) was estimated for supervised fuzzy c-means (FCM) algorithm with this composite measure. With this optimized parameter value of weighted constant (m*) the best similarity or dissimilarity measure function was implemented with the supervised FCM classification and the accuracy assessment of the obtained classified results were obtained
The cluster cores generated by FCM was such that if the distance between the pixel and the cluster centre of the concerned class was less than a defined threshold (α-cut value), that pixel would be belonging to that class with membership grade value of 1

Summary

Introduction

Remote-sensing image data are classified to generate user-defined labels [1]. A land use/land cover (LULC) map is required for land-use planning, for producing land cover maps, to check the health of the crops, etc. Many factors affect the classification of remotely-sensed image data into a thematic map such as the approach for image processing and classification, the quality and selection of remotely-sensed data, the topography of the terrain, etc. These factors affect the accuracy of the classification. Classifying a remote-sensing image into a thematic map is a big challenge as there are many factors involved like: landscape complexity, specification of the data used, the algorithms used for image processing and classification [4], etc. Classifying a remote-sensing image into a thematic map is a big challenge as there are many factors involved like: landscape complexity, specification of the data used, the algorithms used for image processing and classification [4], etc. and these factors may affect the success of classification [5,6]

Objectives

Methods

Results

Conclusion