Principal Component Analysis for Remotely Sensed Data Classified by Kohonen's Feature Mapping Pre-processor and Multi-Layered Neural Network Classifier

スポンサーリンク

概要

• 論文の詳細を見る

• There have been many developments on neural network research, and ability of a multi-layered network for classification of multi-spectral image data has been studied. We can classify non-Gaussian distributed data using the neural network trained by a back-propagation method (BPM) because it is independent of noise conditions. The BPM is a supervised classifier, so that we can get a high classification accuracy by using the method, so long as we can choose the good training data set. However, the multi-spectral data have many kinds of category information in a pixel because of its pixel resolution of the sensor. The data should be separated in many clusters even if they belong to a same class. Therefore, it is difficult to choose the good training data set which extract the characteristics of the class. Up to now, the researchers have chosen the training data set by random sampling from the input data. To overcome the problem, a hybrid pattern classification system using BPM and Kohonens feature mapping (KFM) has been proposed recently. The system performed choosing the training data set from the result of rough classification using KFM. However, how the remotely sensed data had been influenced by the KFM has not been demonstrated quantitatively. In this paper, we propose a new approach using the competitive weight vectors as the training data set, because we consider that a competitive unit represents a small cluster of the input patterns. The approach makes the training data set choice work easier than the usual one, because the KFM can automatically self-organize a topological relation among the target image patterns on a competitive plane. We demonstrate that the representative of the competitive units by principal component analysis (PCA). We also illustrate that the approach improves the classification accuracy by applying it on the classification of the real remotely sensed data.

• 社団法人電子情報通信学会の論文
• 1995-12-25

著者

• Murai H

  Shikoku University

• Oe Shunichiro

  Faculty Of Engineering University Of Tokushima

• Oe Shunichiro

  Faculty Of Engineering The University Of Tokushima

• MURAI HIROSHI

  Faculty of Science and Engineering, Ritsumeikan University

• Murai Hiroshi

  Shikoku University

• Omatu Sigeru

  College of Engineering, Osaka Prefecture University

• Omatu Sigeru

  College Of Engineering Osaka Prefecture University

• Murai Hiroshi

  Faculty Of Science And Engineering Ritsumeikan University

関連論文

• Bacterial Flora of the Biofilm Formed on the Submerged Surface of the Reed Phragmites australis
• An Application of Continuous weights to Phase Unwrapping
• Mountain Areas Extraction by Introduction of Wavelet Transform and Its Application to Ridge Lines Detection
• Liquid-Crystalline Properties of Alkyl 4-[2-(Perfluorooctyl)ethoxy]benzoates
• Synthesis and Thermal Properties of Some Benzenes Incorporating a Perfluoroalkyl Chain
• Principal Component Analysis for Remotely Sensed Data Classified by Kohonen's Feature Mapping Pre-processor and Multi-Layered Neural Network Classifier
• Segmentation of Texture Image by Combining Multiple Segmentation Results
• Texture Image Segmentation by Detecting Texture Edges
• Texture Image Segmentation Method Based on Multi-layer CNN (臨場感を高める最近の映像技術論文特集号)

スポンサーリンク