1) The document describes a system for hand gesture recognition using support vector machines. It uses Canny's edge detection algorithm and histogram of gradients (HOG) for feature extraction from input images of hand gestures.
2) The system is trained using a dataset of predefined hand gestures. During testing, it compares the features extracted from new input images to those in the training dataset and classifies the gesture using an SVM classifier.
3) Experimental results found the system could accurately recognize 20 different static hand gestures in complex backgrounds. However, the authors note that future work could focus on real-time gesture recognition and reducing complexity for faster processing.