File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/DMAMH.2007.4414578
- Scopus: eid_2-s2.0-48349145876
Supplementary
-
Citations:
- Scopus: 0
- Appears in Collections:
Conference Paper: LDA based method for online punch segmentation and recognition
Title | LDA based method for online punch segmentation and recognition |
---|---|
Authors | |
Issue Date | 2007 |
Citation | Proceedings - 2nd Workshop on Digital Media and its Application in Museum and Heritage, DMAMH 2007, 2007, p. 338-343 How to Cite? |
Abstract | In this paper, we propose an approach for real-time online segmentation and recognition of ten typical types of punches from continuously captured boxing sequences. Complete punch patterns are firstly segmented from continuous boxing sequences. Punches from different subjects, which are of variable arm and body length are normalized and uniformly represented with a vector. Then a LDA based punch type recognizer is applied to the unified punches. The type of a specific punch is determined according to a nearest neighbor rule in the LDA feature space. The proposed approach works efficiently and the recognition accuracy is about 98%. We have implemented a real-time online punch recognition system. © 2007 IEEE. |
Persistent Identifier | http://hdl.handle.net/10722/288970 |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Shuxu, Jing | - |
dc.contributor.author | Howard, Leung | - |
dc.contributor.author | Fazhi, He | - |
dc.contributor.author | Komura, Taku | - |
dc.contributor.author | Jacky, Chan | - |
dc.date.accessioned | 2020-10-12T08:06:20Z | - |
dc.date.available | 2020-10-12T08:06:20Z | - |
dc.date.issued | 2007 | - |
dc.identifier.citation | Proceedings - 2nd Workshop on Digital Media and its Application in Museum and Heritage, DMAMH 2007, 2007, p. 338-343 | - |
dc.identifier.uri | http://hdl.handle.net/10722/288970 | - |
dc.description.abstract | In this paper, we propose an approach for real-time online segmentation and recognition of ten typical types of punches from continuously captured boxing sequences. Complete punch patterns are firstly segmented from continuous boxing sequences. Punches from different subjects, which are of variable arm and body length are normalized and uniformly represented with a vector. Then a LDA based punch type recognizer is applied to the unified punches. The type of a specific punch is determined according to a nearest neighbor rule in the LDA feature space. The proposed approach works efficiently and the recognition accuracy is about 98%. We have implemented a real-time online punch recognition system. © 2007 IEEE. | - |
dc.language | eng | - |
dc.relation.ispartof | Proceedings - 2nd Workshop on Digital Media and its Application in Museum and Heritage, DMAMH 2007 | - |
dc.title | LDA based method for online punch segmentation and recognition | - |
dc.type | Conference_Paper | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1109/DMAMH.2007.4414578 | - |
dc.identifier.scopus | eid_2-s2.0-48349145876 | - |
dc.identifier.spage | 338 | - |
dc.identifier.epage | 343 | - |