Static hand pose recognition using Neocognitron and Multi-layer Perceptron Neural networks

• Grant number: 08/01410-0
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: August 01, 2008
• End date: July 31, 2009
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computer Systems
• Principal Investigator: Ednaldo Brigante Pizzolato
• Grantee: Mauro dos Santos Anjo
• Host Institution: Centro de Ciências Exatas e de Tecnologia (CCET). Universidade Federal de São Carlos (UFSCAR). São Carlos , SP, Brazil

Abstract

The goal of this project is to compare two neural network models: Neocognitron - (Fukushima, 1991) and Multi-layer Perceptron in the hand pose recognition. It aims at maximizing the recognition rates and minimizing the false positives. Static hand pose gestures (such as Libra) will be used in this project. Therefore, a photo database with many different poses, hand sizes, skin colors, light conditions, backgrounds will be created. One possible outcome of the project will be real time hand pose recognition through the use of a webcam. That would help building a multimodal user interface.