Abstract
In this paper, we present a new clustering method for segmentations of moving target and non-target objects. We assume that the moving target object has the following conditions: (1) object motion data continuity inter-frame, and (2) object motion data continuity intra-frame. In our model, clusters tend to form as filling these two conditions. The experimental results showed the effectiveness of the proposed algorithm and the performance of this model in terms of the quality of the recognition results. Our algorithm is able to clean the input noise by removing non-target objects before the recognition process.
| Original language | English |
|---|---|
| Pages (from-to) | 213-224 |
| Number of pages | 12 |
| Journal | Neurocomputing |
| Volume | 51 |
| DOIs | |
| Publication status | Published - 2003 Apr |
Fingerprint
Keywords
- Gesture recognition
- Maximum neural networks
- Object segmentation
ASJC Scopus subject areas
- Artificial Intelligence
- Cellular and Molecular Neuroscience
Cite this
Object segmentation using maximum neural networks for the gesture recognition system. / Yoshiike, Noriko; Takefuji, Yoshiyasu.
In: Neurocomputing, Vol. 51, 04.2003, p. 213-224.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - Object segmentation using maximum neural networks for the gesture recognition system
AU - Yoshiike, Noriko
AU - Takefuji, Yoshiyasu
PY - 2003/4
Y1 - 2003/4
N2 - In this paper, we present a new clustering method for segmentations of moving target and non-target objects. We assume that the moving target object has the following conditions: (1) object motion data continuity inter-frame, and (2) object motion data continuity intra-frame. In our model, clusters tend to form as filling these two conditions. The experimental results showed the effectiveness of the proposed algorithm and the performance of this model in terms of the quality of the recognition results. Our algorithm is able to clean the input noise by removing non-target objects before the recognition process.
AB - In this paper, we present a new clustering method for segmentations of moving target and non-target objects. We assume that the moving target object has the following conditions: (1) object motion data continuity inter-frame, and (2) object motion data continuity intra-frame. In our model, clusters tend to form as filling these two conditions. The experimental results showed the effectiveness of the proposed algorithm and the performance of this model in terms of the quality of the recognition results. Our algorithm is able to clean the input noise by removing non-target objects before the recognition process.
KW - Gesture recognition
KW - Maximum neural networks
KW - Object segmentation
UR - http://www.scopus.com/inward/record.url?scp=0037382406&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0037382406&partnerID=8YFLogxK
U2 - 10.1016/S0925-2312(02)00617-3
DO - 10.1016/S0925-2312(02)00617-3
M3 - Article
VL - 51
SP - 213
EP - 224
JO - Neurocomputing
JF - Neurocomputing
SN - 0925-2312
ER -