Title: Fuzzy-based approach to incorporate spatial constraints in possibilistic c-means algorithm for remotely sensed imagery

Authors: Abhishek Singh; Anil Kumar

Addresses: Photogrammetry and Remote Sensing Department (PRSD), Indian Institute of Remote Sensing (IIRS), Indian Space Research Organisation (ISRO), Dehradun, 248001, India ' Photogrammetry and Remote Sensing Department (PRSD), Indian Institute of Remote Sensing (IIRS), Indian Space Research Organisation (ISRO), Dehradun, 248001, India

Abstract: This paper presents a robust possibilistic c-means with constraints (PCM-S) algorithms in a supervised way for remotely sensed imagery. The PCM-S overcome the disadvantages of PCM, by incorporating local information through spatial constraints to control the effect of neighbouring terms. PCM-S has been deployed by adding spatial constraints in order to provide robustness to noise and outliers. Neighbourhood labelling has been done in PCM-S by introducing local window (N_R) and regulariser parameter (η_i). Experiments have been conducted on Formosat-2 satellite imagery of Haridwar area in which classified results of PCM and PCM-S is optimised using mean membership difference (MMD) method and performance of classifiers are analysed using root mean square (RMSE) method. Experiments performed on 1% salt and pepper noisy image and original image show that PCM-S classifier is effective in minimising noisy pixels which produces least RMSE than PCM.

Keywords: possibilistic c-means; PCM; possibilistic c-means with constraints; PCM-S; regularisation parameter; mean membership difference; MMD; root mean square error; RMSE.

DOI: 10.1504/IJIIDS.2020.109459

International Journal of Intelligent Information and Database Systems, 2020 Vol.13 No.2/3/4, pp.307 - 318

Received: 25 Mar 2019
Accepted: 29 Oct 2019
Published online: 09 Sep 2020 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article