Object recognition by discriminative combinations of line segments, ellipses, and appearance features
We present a novel contour-based approach that recognizes object classes in real-world scenes using simple and generic shape primitives of line segments and ellipses. Compared to commonly used contour fragment features, these primitives support more efficient representation since their storage requi...
Saved in:
Main Authors: | Chia, Alex Yong Sang, Rahardja, Susanto, Rajan, Deepu, Leung, Maylor Karhang |
---|---|
其他作者: | School of Computer Engineering |
格式: | Article |
語言: | English |
出版: |
2013
|
主題: | |
在線閱讀: | https://hdl.handle.net/10356/99321 http://hdl.handle.net/10220/13495 |
標簽: |
添加標簽
沒有標簽, 成為第一個標記此記錄!
|
機構: | Nanyang Technological University |
語言: | English |
相似書籍
-
Edge curvature and convexity based ellipse detection method
由: Leung, Maylor Karhang, et al.
出版: (2013) -
Learning discriminative hierarchical features for object recognition
由: Wang, Gang, et al.
出版: (2014) -
Human action recognition using pose-based discriminant embedding
由: Saghafi, Behrouz, et al.
出版: (2013) -
Salient object detection through over-segmentation
由: Zhang, Xuejie, et al.
出版: (2013) -
Discriminant feature analysis for pattern recognition
由: HUANG DONG
出版: (2010)