TY - GEN
T1 - Combining hierarchical segmentation and shape context based recognition
AU - Yang, Fenglei
AU - Lu, Yue
AU - Duan, Ye
PY - 2008
Y1 - 2008
N2 - In this paper, we integrate image segmentation and object recognition into one unified process. The process starts from a seed region produced by the initial segmentation. Then it is evolved through alternating shape context based recognition and smaller scale image segmentation, until an object is found. In recognition, the thin plate spline (TPS) transformation is employed to locate the difference between the seed region and the defined model, and guide the subsequent evolution process. Experimental results demonstrate the advantages achieved by the combination of hierarchical segmentation and multi-scale shape contexts based recognition.
AB - In this paper, we integrate image segmentation and object recognition into one unified process. The process starts from a seed region produced by the initial segmentation. Then it is evolved through alternating shape context based recognition and smaller scale image segmentation, until an object is found. In recognition, the thin plate spline (TPS) transformation is employed to locate the difference between the seed region and the defined model, and guide the subsequent evolution process. Experimental results demonstrate the advantages achieved by the combination of hierarchical segmentation and multi-scale shape contexts based recognition.
UR - https://www.scopus.com/pages/publications/51849112857
U2 - 10.1109/CIT.2008.4594783
DO - 10.1109/CIT.2008.4594783
M3 - 会议稿件
AN - SCOPUS:51849112857
SN - 9781424423583
T3 - Proceedings - 2008 IEEE 8th International Conference on Computer and Information Technology, CIT 2008
SP - 839
EP - 844
BT - Proceedings - 2008 IEEE 8th International Conference on Computer and Information Technology, CIT 2008
T2 - 2008 IEEE 8th International Conference on Computer and Information Technology, CIT 2008
Y2 - 8 July 2008 through 11 July 2008
ER -