A Randomized Hypercolumn Model and Gesture Recognition

Authors:
Naoyuki Tsuruta;Yuichiro Yoshiki;Tarek El. Tobely
Affiliations:
-;-;-
Venue:
IWANN '01 Proceedings of the 6th International Work-Conference on Artificial and Natural Neural Networks: Connectionist Models of Neurons, Learning Processes and Artificial Intelligence-Part I
Year:
2001

Citing 3
Cited 0

Recognizing hand gestures

ECCV '94 Proceedings of the third European conference on Computer vision (vol. 1)
Self-Organizing Maps

Self-Organizing Maps
Hypercolumn Model: A Modified Model of Neocognitron Using Hierarchical Self-Oragnizing Maps

IWANN '99 Proceedings of the International Work-Conference on Artificial and Natural Neural Networks: Foundations and Tools for Neural Modeling

Quantified Score

Hi-index	0.00

Visualization

Abstract

Gesture recognition is an appealing tool for natural interface with computers especially for physically impaired persons. In this paper, it is proposed to use Hypercolumn model (HCM), which is constructed by hierarchically piling up Self-organizing maps (SOM), as an image recognition system for gesture recognition, since the HCM allows alleviating many difficulties associated with gesture recognition. It is, however, required for on-line systems to reduce the recognition time to the range of normal video camera rates. To achieve this, the Randomized HCM (RHCM), which is derived from HCM by replacing SOM with randomized SOM, is introduced. With RHCM algorithm, the recognition time is drastically reduced without accuracy deterioration. The experimental results to recognize hand gestures using RHCM are presented.