Three-Dimensional Object Recognition Using an Unsupervised Neural Network: 
Understanding the Distinguishing Features

Intrator, N; Gold, JI; Bülthoff, HH; Edelman, S

アイテム詳細

登録内容を編集ファイル形式で保存

一時保存へ追加

タグ情報を表示リリース履歴を表示詳細要約

公開

会議論文

Three-Dimensional Object Recognition Using an Unsupervised Neural Network: Understanding the Distinguishing Features

MPS-Authors

There are no MPG-Authors in the publication available

External Resource

There are no locators available

Fulltext (restricted access)

There are currently no full texts shared for your IP range.

フルテキスト (公開)

Israeli-AICV-8-Buelthoff_01.pdf
(全文テキスト（全般）), 144KB

付随資料 (公開)

There is no public supplementary material available

引用

Intrator, N., Gold, J., Bülthoff, H., & Edelman, S. (1991). Three-Dimensional Object Recognition Using an Unsupervised Neural Network: Understanding the Distinguishing Features. In Y., Feldman, & A., Bruckstein (Eds.), 8th Israeli Conference on AICV (pp. 113-123). Amsterdam, The Netherlands: Elsevier.

引用: https://hdl.handle.net/11858/00-001M-0000-0013-EE65-6

要旨

A novel method for feature extraction has been applied to a problem of three-dimensional object recognition (Intrator and Gold, 1991). The method is related to
recent statistical theory (Huber, 1985; Friedman, 1987) and is derived from a biologically motivated computational theory (Bienenstock, Cooper and Munro,
1982). Results of an initial study replicating recent psychophysical experiments (Bulthoff and Edelman 1991) demonstrated the utility of the proposed method for
feature extraction. We describe further experiments designed to analyze the nature of the extracted features, and their relevance to the theory and psychophysics
of object recognition.