2023 Fiscal Year Final Research Report
Line Drawing and Stylization in Consideration of Human Visual System
Project/Area Number |
20H04203
|
Research Category |
Grant-in-Aid for Scientific Research (B)
|
Allocation Type | Single-year Grants |
Section | 一般 |
Review Section |
Basic Section 61010:Perceptual information processing-related
|
Research Institution | The University of Tokyo |
Principal Investigator |
|
Co-Investigator(Kenkyū-buntansha) |
山田 修 奈良県立大学, 地域創造学部, 特任教授 (30571723)
SRIPIAN PEERAYA 芝浦工業大学, 工学部, 准教授 (70822542)
籔内 直樹 (籔内佐斗司) 東京藝術大学, 大学院美術研究科, 教授 (10376931)
|
Project Period (FY) |
2020-04-01 – 2023-03-31
|
Keywords | 線画 / 視覚特性 / 3次元形状知覚 |
Outline of Final Research Achievements |
We investigated a line drawing method based on a feature line extraction technique using integral property of a curved surface. Furthermore, we tried a method to generate line drawings by machine learning based on a set of 3D shape data and line drawings drawn by humans. In addition, we analyzed the sense of depth obtained from angles of lines and vanishing points in line drawings with regard to their scale, and also examined the use of these properties for line drawing effects. In particular, we investigated the tendency of spatial cognition induced by the relationship between multiple lines, such as vanishing points, and obtained knowledge about human characteristics in understanding 3D scenes.
|
Free Research Field |
形状処理,画像処理
|
Academic Significance and Societal Importance of the Research Achievements |
線画表現は多くの場面で必要とされている.たとえば,機械や建造物の設計図,利用マニュアルの説明図などによく用いられる.機械部品などCADデータが存在すれば線画を生成することも可能だが,その場合でも人による修正が必要となっている.一方で自然物や彫像のように複雑な凹凸を持つ曲面形状の場合,適切な線画を自動的に生成することは困難である.また形状理解を促すために設計図や説明図では線幅や描き方に変化をつけるが,その調整法も自明ではない.本研究によって線画認知におけるヒトの特性を解明するとともに,その特性を利用した線画生成ならびに線画への効果付与技術への端緒が得られた.
|