変形股関節を対象とした多階層統計的形状モデルによる3次元CT画像からの大腿骨領域の半自動抽出

概要

論文の詳細を見る
The Self Organizing Map (SOM) is one of the most widely used neural network paradigm based on unsupervised competitive learning and can be utilized in a broad area of pattern recognition domain. Though SOM is used in some face recognition applications, it still did not utilized against pose and illumination variations in face based applications. In this paper we use SOM as a feature extractor and SVM as a feature recognizer to perform a complete face recognition system across pose and illumination. To validate our system we use the CMU-PIE database and make a comparison between our approach and other reported approach.
2007-02-15