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, lig…