Characterising the Thematic Content of Image Pixels with Topologically Structured Clustering

The location of a pixel in feature space is a function of its thematic composition. The latter is central to an image classification analysis, notably as an input (e.g., training data for a supervised classifier) and/or an output (e.g., predicted class label). Whether as an input to or output from a...

Ful tanımlama

Detaylı Bibliyografya
Yazar: Giles M. Foody
Materyal Türü: Makale
Dil:English
Baskı/Yayın Bilgisi: MDPI AG 2025-01-01
Seri Bilgileri:Remote Sensing
Konular:
Online Erişim:https://www.mdpi.com/2072-4292/17/1/130
_version_ 1826882820254990336
author Giles M. Foody
author_facet Giles M. Foody
author_sort Giles M. Foody
collection DOAJ
description The location of a pixel in feature space is a function of its thematic composition. The latter is central to an image classification analysis, notably as an input (e.g., training data for a supervised classifier) and/or an output (e.g., predicted class label). Whether as an input to or output from a classification, little if any information beyond a class label is typically available for a pixel. The Kohonen self-organising feature map (SOFM) neural network however offers a means to both cluster together spectrally similar pixels that can be allocated suitable class labels and indicate relative thematic similarity of the clusters generated. Here, the thematic composition of pixels allocated to clusters represented by individual SOFM output units was explored with two remotely sensed data sets. It is shown that much of the spectral information of the input image data is maintained in the production of the SOFM output. This output provides a topologically structured representation of the image data, allowing spectrally similar pixels to be grouped together and the similarity of different clusters to be assessed. In particular, it is shown that the thematic composition of both pure and mixed pixels can be characterised by a SOFM. The location of the output unit in the output layer of the SOFM associated with a pixel conveys information on its thematic composition. Pixels in spatially close output units are more similar spectrally and thematically than those in more distant units. This situation also enables specific sub-areas of interest in the SOFM output space and/or feature space to be identified. This may, for example, provide a means to target efforts in training data acquisition for supervised classification as the most useful training cases may have a tendency to lie within specific sub-areas of feature space.
first_indexed 2025-02-17T03:28:54Z
format Article
id doaj.art-1c7f2a3fa2f7435a91f54fd64c29cfd2
institution Directory Open Access Journal
issn 2072-4292
language English
last_indexed 2025-02-17T03:28:54Z
publishDate 2025-01-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj.art-1c7f2a3fa2f7435a91f54fd64c29cfd22025-01-10T13:20:19ZengMDPI AGRemote Sensing2072-42922025-01-0117113010.3390/rs17010130Characterising the Thematic Content of Image Pixels with Topologically Structured ClusteringGiles M. Foody0School of Geography, University of Nottingham, Nottingham NG7 2RD, UKThe location of a pixel in feature space is a function of its thematic composition. The latter is central to an image classification analysis, notably as an input (e.g., training data for a supervised classifier) and/or an output (e.g., predicted class label). Whether as an input to or output from a classification, little if any information beyond a class label is typically available for a pixel. The Kohonen self-organising feature map (SOFM) neural network however offers a means to both cluster together spectrally similar pixels that can be allocated suitable class labels and indicate relative thematic similarity of the clusters generated. Here, the thematic composition of pixels allocated to clusters represented by individual SOFM output units was explored with two remotely sensed data sets. It is shown that much of the spectral information of the input image data is maintained in the production of the SOFM output. This output provides a topologically structured representation of the image data, allowing spectrally similar pixels to be grouped together and the similarity of different clusters to be assessed. In particular, it is shown that the thematic composition of both pure and mixed pixels can be characterised by a SOFM. The location of the output unit in the output layer of the SOFM associated with a pixel conveys information on its thematic composition. Pixels in spatially close output units are more similar spectrally and thematically than those in more distant units. This situation also enables specific sub-areas of interest in the SOFM output space and/or feature space to be identified. This may, for example, provide a means to target efforts in training data acquisition for supervised classification as the most useful training cases may have a tendency to lie within specific sub-areas of feature space.https://www.mdpi.com/2072-4292/17/1/130ground datareference datatraining sitesunsupervised classificationsupervised classificationKohonen neural network
spellingShingle Giles M. Foody
Characterising the Thematic Content of Image Pixels with Topologically Structured Clustering
Remote Sensing
ground data
reference data
training sites
unsupervised classification
supervised classification
Kohonen neural network
title Characterising the Thematic Content of Image Pixels with Topologically Structured Clustering
title_full Characterising the Thematic Content of Image Pixels with Topologically Structured Clustering
title_fullStr Characterising the Thematic Content of Image Pixels with Topologically Structured Clustering
title_full_unstemmed Characterising the Thematic Content of Image Pixels with Topologically Structured Clustering
title_short Characterising the Thematic Content of Image Pixels with Topologically Structured Clustering
title_sort characterising the thematic content of image pixels with topologically structured clustering
topic ground data
reference data
training sites
unsupervised classification
supervised classification
Kohonen neural network
url https://www.mdpi.com/2072-4292/17/1/130
work_keys_str_mv AT gilesmfoody characterisingthethematiccontentofimagepixelswithtopologicallystructuredclustering