Márcio Leandro Gonçalves

Data Clustering using Self-Organizing Maps segmented by Mathematic Morphology and Simplified Cluster Validity Indexes: an application in remotely sensed images

This paper presents a cluster analysis method which automatically finds the number of clusters as well as the partitioning of a data set without any type of interaction with the user. The data clustering is made using the self-organizing (or Kohonen) map (SOM). Different partitions of the trained SOM are obtained from different segmentations of the U-matrix (a neuron-distance image) that are generated by means of mathematical morphology techniques. The different partitions of the trained SOM produce different partitions for the data set which are evaluated by cluster validity indexes. To reduce the computational cost of the cluster analysis process this work also proposes the simplification of cluster validity indexes using the statistical properties of the SOM. The proposed methodology is applied in the cluster analysis of remotely sensed images.

A neural architecture for the classification of remote sensing imagery with advanced learning algorithms

This work presents an artificial neural networks based architecture for the classification of remote sensing (RS) multispectral imagery. The architecture consists of two processing modules: an image feature extraction module using Kohonen self-organizing map and a classification module using multilayer perceptron network. The architecture was developed aiming at two specific goals: to exploit the advantages of unsupervised learning for feature extraction, and the testing of techniques to increase the learning algorithms performance concerning training time. To test the applicability of this work, the architecture was applied to the classification of a LANDSAT/TM image segment from a pre-selected testing area and its performance was compared with that of a maximum likelihood classifier, conventionally used for RS multispectral images classification.

Automatic remotely sensed data clustering by tree-structured self-organizing maps

This work presents a clusters analysis method which automatically finds the number of clusters as well as the partitioning of data set in a remotely sensed image without any type of assistance of an image analyst. The data clustering is made using the self-organizing (or Kohonen) map (SOM) and the techniques proposed by Costa & Netto (2001) for automatic partition of trained SOM networks and for generating a hierarchy of maps based on the detected data clusters. The proposed clustering method has been applied on a LANDSAT/TM image and its performance was compared with that of K-means algorithm, conventionally used for remotely sensed images.

Visualização e Análise de Agrupamentos Usando Redes Auto-Organizáveis, Segmentação de Imagens e Índices de Validação

Self-organizing maps (SOM) had been widely used for input data quantization and visual display of data, an important property that does not exist in most of clustering algorithms. Effective data clustering using SOM involves two or three steps procedure. After proper network training, units can be clustered generating regions of neurons which are related to data clusters. The basic assumption relies on the data density approximation by the neurons through unsupervised learning. The transformation of high dimensional data into images and its visualization and clustering is addressed in this paper. The proposed method segments SOM networks via watershed algorithms and modified cluster validation indexes. Results are shown for benchmark datasets for different map sizes. KeywordsSelf-organizing maps, visualization, data clustering, validation indexes, neural networks, pattern recognition.

Cluster Analysis of Land-Cover Images Using Automatically Segmented SOMs with Textural Information

This work attempts to take advantage of the properties of Kohonens Self-Organizing Map (SOM) to perform the cluster analysis of remotely sensed images. A clustering method which automatically finds the number of clusters as well as the partitioning of the image data is proposed. The data clustering is made using the SOM. Different partitions of the trained SOM are obtained from different segmentations of the U-matrix (a neuron-distance image) that are generated by means of mathematical morphology techniques. The different partitions of the trained SOM produce different partitions for the image data which are evaluated by cluster validity indexes. Seeking to guarantee even greater efficiency in the image categorization process, the proposed method extracts information from the image by means of pixel windows, in order to incorporate textural information. The experimental results show an application example of the proposed method on a TM-Landsat image.

A three-stage approach based on the self-organizing map for satellite image classification

This work presents a methodology for the land-cover classification of satellite images based on clustering of the Kohonens self-organizing map (SOM). The classification task is carried out using a three-stage approach. At the first stage, the SOM is used to quantize and to represent the original patterns of the image in a space of smaller dimension. At the second stage of the method, a filtering process is applied on the SOM prototypes, wherein prototypes associated to input patterns that incorporate more than one land cover class and prototypes that have null activity are excluded in the next stage or simply eliminated of the analysis. At the third and last stage, the SOM prototypes are segmented through a hierarchical clustering method which uses the neighborhood relation of the neurons and incorporates spatial information in its merging criterion. The experimental results show an application example of the proposed methodology on an IKONOS image.

A Neural System for Remote Sensing Multispectral Image Classification

This work presents a system for Remote Sensing (RS) multispectral image classification based on Artificial Neural Networks (ANN), aiming at two objectives, namely: searching of techniques for improving the performance in the classification task and to exploit the advantages of unsupervised learning for feature extraction. The system is divided in two phases: feature extraction by the Kohonen Self -Organizing Map (SOM) and classification by a Multilayer Perceptron (MLP) network, trained by a learning algorithm which uses 2nd-order information exactly calculated. To evaluate the efficiency of this classification scheme, a comparative analysis with the maximum likelihood algorithm, conventionally used for RS multispectral images classification, is realized.