Image transformation using a feature map of multiply descent cost competitive learning

Yasuo Matsuyama

研究成果: Conference contribution

抜粋

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.

元の言語English
ホスト出版物のタイトルProceedings. IJCNN - International Joint Conference on Neural Networks
編集者 Anon
出版場所Piscataway, NJ, United States
出版者Publ by IEEE
ページ936
ページ数1
ISBN(印刷物)0780301641
出版物ステータスPublished - 1992
外部発表Yes
イベントInternational Joint Conference on Neural Networks - IJCNN-91-Seattle - Seattle, WA, USA
継続期間: 1991 7 81991 7 12

Other

OtherInternational Joint Conference on Neural Networks - IJCNN-91-Seattle
Seattle, WA, USA
期間91/7/891/7/12

ASJC Scopus subject areas

  • Engineering(all)

フィンガープリント Image transformation using a feature map of multiply descent cost competitive learning' の研究トピックを掘り下げます。これらはともに一意のフィンガープリントを構成します。

  • これを引用

    Matsuyama, Y. (1992). Image transformation using a feature map of multiply descent cost competitive learning. : Anon (版), Proceedings. IJCNN - International Joint Conference on Neural Networks (pp. 936). Publ by IEEE.