We present a self-organizing framework called the SHOSLIF-M for learning and recognizing spatiotemporal events (or patterns) from intensity image sequences. The proposed framework consists of a multiclass, multivariate discriminant analysis to automatically select the most discriminating features (MDF), a space partition tree to achieve a logarithmic retrieval time complexity for a database of n items, and a general interpolation scheme to do view inference and generalization in the MDF space based on a small number of training samples. The system is tested to recognize 28 different hand signs. The experimental results show that the learned system can achieve a 96% recognition rate for test sequences that have not been used in the training phase.<>
Learning-based hand sign recognition using SHOSLIF-M
1995-01-01
587686 byte
Conference paper
Electronic Resource
English
Learning-Based Hand Sign Recognition Using SHOSLIF-M
British Library Conference Proceedings | 1995
|Appearance-Based Hand Sign Recognition from Intensity Image Sequences
British Library Online Contents | 2000
|Control of Home Appliances Using Face and Hand Sign Recognition
British Library Conference Proceedings | 2001
|