Interval Type-2 Fuzzy C-Means Clustering with Spatial Information for Land-Cover Classification

Mai, Dinh Sinh; Ngo, Long Thanh

doi:10.1007/978-3-319-15702-3_38

Cited by 12 publications

(12 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, some studies have improved the IT2FCM algorithm for satellite image classification. Accordingly, in [38,40], a new distance was introduced to replace the traditional Euclidean distance in the IT2FCM algorithm using spectral and spatial information in multispectral remote sensing image clustering. In [39], the SIIT2FCM algorithm was expanded from IIT2FCM [38] to change detection on multispectral satellite images that used spatial information and the semi-supervised method to improve the accuracy of classification results.…”

Section: Introductionmentioning

confidence: 99%

“…Accordingly, in [38,40], a new distance was introduced to replace the traditional Euclidean distance in the IT2FCM algorithm using spectral and spatial information in multispectral remote sensing image clustering. In [39], the SIIT2FCM algorithm was expanded from IIT2FCM [38] to change detection on multispectral satellite images that used spatial information and the semi-supervised method to improve the accuracy of classification results. Some studies developed the IT2FCM algorithm mentioned in [33,41] using the multiple kernel technique for data classification.…”

Section: Introductionmentioning

confidence: 99%

“…The common point of the studies [38,39,45,46] is that they all use information about the spatial relationship between pixels to improve the objective function, while MFs also have a significant influence on which cluster the pixels will belong to. The work reported in [45,46] used type-1 fuzzy MFs limited to describing uncertain data.…”

Section: Introductionmentioning

confidence: 99%

“…The studies used spatial weights to calculate each pixel's influence in the clustering process. Meanwhile, [38,39] developed FCM algorithms based on IT2FSs, which could overcome the disadvantage of T1FSs in describing uncertain data. However, both of these studies used only fuzzy MFs.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A hybrid interval type-2 semi-supervised possibilistic fuzzy c-means clustering and particle swarm optimization for satellite image analysis

Mai

Ngo

Hung

et al. 2021

Information Sciences

Self Cite

View full text Add to dashboard Cite

Although satellite images can provide more information about the Earth's surface in a relatively short time and over a large scale, they are affected by observation conditions (e.g., wind, sun, rain, and humidity) and the accuracy of the image acquisition equipment. The objects on the images are often unclear and uncertain, especially at their borders. The fuzzy clustering technique allows each data pattern to belong to many different clusters through membership function (MF) values that can handle data patterns with unclear and uncertain boundaries well. However, this technique is quite sensitive to noise, outliers, and limitations in handling uncertainties. Furthermore, the membership degrees of type-1 fuzzy sets (T1FSs) are crisp, and in many cases, it is difficult to precisely determine the T1FS parameters. To overcome these disadvantages, we propose a hybrid method encompassing interval type-2 semi-supervised possibilistic fuzzy c-means clustering (IT2SPFCM) and particle swarm optimization (PSO) to form the proposed IT2SPFCMPSO. We experimented on several satellite images (Landsat-5 TM, Landsat-7 ETM+, Landsat-8, Sentinel-2A) to prove the effectiveness of the proposed method. Experimental results show that the IT2SPFCM-PSO algorithm achieves accuracies from 98.8% to 99.39%, which are higher than those of other matching algorithms. An analysis of the results by indicators PC-I, CE-I, D-I, XB-I, τ − I, and MSE also showed that the proposed method achieves better results in most experiments.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A hybrid interval type-2 semi-supervised possibilistic fuzzy c-means clustering and particle swarm optimization for satellite image analysis

Mai

Ngo

Hung

et al. 2021

Information Sciences

Self Cite

View full text Add to dashboard Cite

show abstract

“…Yu et al applied IT2FCM earlier to solve the problem of remote sensing data processing [10]. Mai et al used the spatial information between pixels to calculate the interval-valued membership degree, and proposed an improved IIT2FCM to solve the problem of land cover segmentation from multispectral satellite images [11]. Ngo et al proposed a semi-supervised interval type-2 fuzzy c-means clustering (SIIT2FCM) with spatial information constraints, and it is applied to land cover segmentation from multispectral remote sensing images [12].…”

mentioning

confidence: 99%

A Novel Single Fuzzifier Interval Type-2 Fuzzy C-Means Clustering With Local Information for Land-Cover Segmentation

Guo

2021

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

In the process of land cover segmentation from remote sensing image, there are some uncertainties such as "significant difference in class density", "different objects with same spectrum" and "same object with different spectra". Existing fuzzy c-means clustering is not sufficient to describe the high-order fuzzy uncertainties and cannot achieve accurate segmentation. Type-2 fuzzy set is perfect for handling with inter-class multiple uncertainties, and clustering algorithm can suppress the noise of remote sensing image effectively by incorporating local information. Therefore, on the basis of integrating local information, this paper proposes a robust single fuzzifier interval type-2 fuzzy local C-means clustering based on adaptive interval-valued data for land cover segmentation. Firstly, interval-valued data modeling is performed for remote sensing data, and remote sensing features are represented as interval-valued vectors, and the robust interval-valued distance measure that can maximize the distance between interval-valued numbers is used to generate an interval type-2 fuzzy set through robust fuzzy clustering. Secondly, this paper adopts an efficient type reduction method to seek equivalent type-1 fuzzy set adaptively, and realizes the segmentation of land cover by the principle of maximum type-1 fuzzy membership. The test results of multi-spectral remote sensing images show that the segmentation performance of this proposed algorithm outperforms existing state of the art adaptive interval type-2 fuzzy clustering algorithms, and it is beneficial to the interpretation of remote sensing image. Index Terms-fuzzy C-means clustering; interval-valued data; interval type-2 fuzzy sets; fuzzy local information; land cover segmentation. I. INTRODUCTIONuzzy theory, as the basis of fuzzy analysis, is constantly updated and developed. The defects of type-1 fuzzy clustering algorithm in dealing with uncertainty are gradually exposed, and type-2 fuzzy clustering algorithm has certain potential advantage in dealing with high order uncertainty. Zadeh introduced type-2 fuzzy set (T2FS) as the extension of the concept of ordinary fuzzy set. In essence, it is a "fuzzy fuzzy set". In particular, type 2 fuzzy set is widely used to deal

show abstract

Approach the Interval Type-2 Fuzzy System and PSO Technique in Landcover Classification

Mai

Ngo

Hung

2020

Intelligent Information and Database Systems

View full text Add to dashboard Cite

Interval Type-2 Fuzzy C-Means Clustering with Spatial Information for Land-Cover Classification

Cited by 12 publications

References 13 publications

A hybrid interval type-2 semi-supervised possibilistic fuzzy c-means clustering and particle swarm optimization for satellite image analysis

A hybrid interval type-2 semi-supervised possibilistic fuzzy c-means clustering and particle swarm optimization for satellite image analysis

A Novel Single Fuzzifier Interval Type-2 Fuzzy C-Means Clustering With Local Information for Land-Cover Segmentation

Approach the Interval Type-2 Fuzzy System and PSO Technique in Landcover Classification

Contact Info

Product

Resources

About