Enhanced Spatially Constrained Remotely Sensed Imagery Classification Using a Fuzzy Local Double Neighborhood Information C-Means Clustering Algorithm

This paper presents a fuzzy local double neighborhood information c-means (FLDNICM) clustering algorithm for remotely sensed imagery classification, which incorporates flexible and accurate local spatial and spectral information. First, a tradeoff weighted fuzzy factor is established based on a pixe...

Full description

Saved in:
Bibliographic Details
Published in:IEEE journal of selected topics in applied earth observations and remote sensing Vol. 11; no. 8; pp. 2896 - 2910
Main Authors: Zhang, Hua, Bruzzone, Lorenzo, Shi, Wenzhong, Hao, Ming, Wang, Yunjia
Format: Journal Article
Language:English
Published: Piscataway IEEE 01.08.2018
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Algorithms
Blurring
Classification
Clustering
Clustering algorithms
Clustering methods
Conditional probability
Dependence
fuzzy c-means (FCM) clustering
Fuzzy logic
Image classification
Image edge detection
Image enhancement
Image processing
Image segmentation
Imagery
Linear programming
neighborhood
Noise measurement
Pixels
prior probability
Probability theory
Remote sensing
remotely sensed imagery
Robustness
Robustness (mathematics)
Tradeoffs
ISSN:1939-1404, 2151-1535
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper presents a fuzzy local double neighborhood information c-means (FLDNICM) clustering algorithm for remotely sensed imagery classification, which incorporates flexible and accurate local spatial and spectral information. First, a tradeoff weighted fuzzy factor is established based on a pixel spatial attraction model that considers spatial distance and class membership differences between the central pixel and its neighbor simultaneously. This factor can adaptively and accurately estimate the spatial constraints from neighboring pixels. To further enhance robustness to noise and outliers, another fuzzy prior probability function is also defined, which integrates the mutual dependence information from a pixel and its neighbor in a fuzzy logical way for obtaining accurate spatial contextual information. The FLDNICM enhances the conventional fuzzy c-means algorithm by producing homogeneous segmentation while reducing the edge blurring artifacts. The new trade-off weighted fuzzy factor and prior probability function are both parameter free and fully adaptive to the image content. Experimental results demonstrate the superiority of FLDNICM over competing methodologies, considering a series of synthetic and real-world images classification applications.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1939-1404
2151-1535
DOI:10.1109/JSTARS.2018.2846603