Publicação
A comparative study of different image features for hand gesture machine learning
| Resumo: | Vision-based hand gesture interfaces require fast and extremely robust hand detection, and gesture recognition. Hand gesture recognition for human computer interaction is an area of active research in computer vision and machine learning. The primary goal of gesture recognition research is to create a system, which can identify specific human gestures and use them to convey information or for device control. In this paper we present a comparative study of seven different algorithms for hand feature extraction, for static hand gesture classification, analysed with RapidMiner in order to find the best learner. We defined our own gesture vocabulary, with 10 gestures, and we have recorded videos from 20 persons performing the gestures for later processing. Our goal in the present study is to learn features that, isolated, respond better in various situations in human-computer interaction. Results show that the radial signature and the centroid distance are the features that when used separately obtain better results, being at the same time simple in terms of computational complexity. |
|---|---|
| Autores principais: | Trigueiros, Paulo |
| Outros Autores: | Ribeiro, A. Fernando; Reis, L. P. |
| Assunto: | Hand gesture recognition Machine vision Hand features Hog Fourier descriptors Centroid distance Radial signature Shi-Thomasi corner detection Shi-tomasi corner detection |
| Ano: | 2013 |
| País: | Portugal |
| Tipo de documento: | comunicação em conferência |
| Tipo de acesso: | acesso aberto |
| Instituição associada: | Universidade do Minho |
| Idioma: | inglês |
| Origem: | RepositóriUM - Universidade do Minho |
| Resumo: | Vision-based hand gesture interfaces require fast and extremely robust hand detection, and gesture recognition. Hand gesture recognition for human computer interaction is an area of active research in computer vision and machine learning. The primary goal of gesture recognition research is to create a system, which can identify specific human gestures and use them to convey information or for device control. In this paper we present a comparative study of seven different algorithms for hand feature extraction, for static hand gesture classification, analysed with RapidMiner in order to find the best learner. We defined our own gesture vocabulary, with 10 gestures, and we have recorded videos from 20 persons performing the gestures for later processing. Our goal in the present study is to learn features that, isolated, respond better in various situations in human-computer interaction. Results show that the radial signature and the centroid distance are the features that when used separately obtain better results, being at the same time simple in terms of computational complexity. |
|---|