抄録
Summary form only given. It was shown that the feature map obtained by multiple descent cost competitive self-organization can be used for the transformation of images combined with the supervision of an outside intelligence. The example of the change of emotional expression of a face was considered. The task of the first module was to locate the prospective edges. Basically, two orthogonally oriented preliminary networks (horizontal and vertical) are sufficient. This is true because a homogeneous region can be outlined using only vertical and horizontal edges. A prospective edge selection (preliminary) network consists of two types of neurons: image neurons and edge neurons. Each image neuron corresponds to a pixel in the image. Between each image neuron is an edge neuron, one corresponding to every possible edge location for the desired orientation. The goal of the vertical network is to find the prospective vertical edges in the horizontal direction.
本文言語 | English |
---|---|
ホスト出版物のタイトル | Proceedings. IJCNN - International Joint Conference on Neural Networks |
編集者 | Anon |
Place of Publication | Piscataway, NJ, United States |
出版社 | Publ by IEEE |
ページ | 936 |
ページ数 | 1 |
ISBN(印刷版) | 0780301641 |
出版ステータス | Published - 1992 |
外部発表 | はい |
イベント | International Joint Conference on Neural Networks - IJCNN-91-Seattle - Seattle, WA, USA 継続期間: 1991 7月 8 → 1991 7月 12 |
Other
Other | International Joint Conference on Neural Networks - IJCNN-91-Seattle |
---|---|
City | Seattle, WA, USA |
Period | 91/7/8 → 91/7/12 |
ASJC Scopus subject areas
- 工学(全般)