Name
Abstract | ||
|---|---|---|
A model to extract a structure feature of images belonging to one category is proposed, implemented and studied. This model consists of two parts i.e. an extraction of partial geometrical features and an extraction of structure feature by using them under the positional constraints. First, necessary conditions which geometrical features should satisfy is stated and a statistical method to select a key feature is described. Then the algorithm to extract structure feature as the maximal set of common subimages which satisfy the positional constraint is introduced. The structure feature is regarded as a intrinsic feature which is used when an animal perceives an image at a glance. The experiment was carried out about image of human faces and had a fairly good results. |
Year | Venue | Keywords |
|---|---|---|
1979 | IJCAI | human face,key feature,structure feature,positional constraint,partial geometrical feature,necessary condition,intrinsic feature,structural image feature,common subimages,good result,geometrical feature |
Field | DocType | ISBN |
Computer vision,Maximal set,Pattern recognition,Feature detection (computer vision),Feature (computer vision),Computer science,Feature extraction,Feature model,Artificial intelligence,Kanade–Lucas–Tomasi feature tracker,Perception,Machine learning | Conference | 0-934613-47-8 |
Citations | PageRank | References |
0 | 0.34 | 2 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Hajime Enomoto | 1 | 53 | 18.27 |
| Naoki Yonezaki | 2 | 107 | 20.02 |
| Katsumi Nitta | 3 | 160 | 44.94 |