Learning Model Structures from Images (Special Issue on Computer Vision)
スポンサーリンク
概要
- 論文の詳細を見る
Based on a newly proposed notion of relational network, a novel learning mechanism for model acquisition is developed. This new mechanism explicitly deals with both qualitative and quantitative relations between parts of an object. Qualitative relations are mirrored in the topology of the network. Quantitative relations appear in the form of generalized predicates, that is, predicates that are graded in their validity over a certain range. Starting from a decomposition of binary objects into meaningful parts, first a description of the decomposition in terms of relational networks is obtained. Based on the description of two or more instances of the same concept, generalizations are obtained by first finding matchings between instances. Generalizing itself proceeds on two levels: the topological and the predicate level. Topological generalization is achieved by a simple rule-based graph generalizer. Generalization of the predicates uses some ideas from MYCIN. After successful generalization, the system attempts to derive a simple and coarse description of the achieved result in terms of near natural language. Several examples underline the validity of relational networks and illustrate the performance of the proposed system.
- 社団法人電子情報通信学会の論文
- 1994-11-25
著者
-
ABE Keiichi
Department of Physics, Saitama University
-
Held Andreas
新情報処理開発機構つくば研究センタ
-
Andreas H
新情報処理開発機構
-
Held Andreas
Graduate School Of Electronic Science And Technology Shizuoka University
-
Abe Keiichi
Department Of Computer Science Shizuoka University
-
Abe Keiichi
Department Of Agricultural Chemistry Faculty Of Agriculture Tokyo University
関連論文
- Suzaku Observations of Abell 1795 : Cluster Emission to r_
- Spectral evolution of GRB 060904A observed with swift and Suzaku : Possibility of inefficient electron acceleration
- The Suzaku-Swift Joint Observation of the Early X-Ray Afterglow of GRB060105(Chapter 1. Gamma Ray Bursts, Cosmic Rays and Neutrino, The Extreme Universe in the Suzaku Era)
- A multiband study of the optically dark GRB 051028
- The X-Ray Observatory Suzaku
- 全方位視覚センサを用いた大局的位置の推定
- タスクに依存しないモデルに基づいた動画像による実時間位置同定
- Hard X-ray Detector (HXD) on board Suzaku
- In-orbit performance of the hard X-ray detector on board Suzaku
- Suzaku Observations of Abell 1795 : Cluster Emission to r_(Chapter 2. Thermal Structure/Dynamics of Groups and Clusters of Galaxies, The Extreme Universe in the Suzaku Era)
- Search for Oxygen Emission from Warm-Hot Intergalactic Medium around A 2218 with Suzaku
- Swift and Suzaku observations of the X-ray afterglow from the GRB 060105
- Radicicol, an Agent Inducing the Reversal of Transformed Phenotypes of src-Transformed Fibroblasts
- Suzaku Observation of the Metallicity Distribution in the Elliptical Galaxy NGC 4636
- Brain Metastasis in Malignant Pleural Mesothelioma Presenting as Intratumoral Hemorrhage : Case Report
- Learning Model Structures from Images (Special Issue on Computer Vision)
- Height and Reliability of Edges
- WIDGET : System Performance and GRB Prompt Optical Observations