Human action recognition using combined contour - based and silhouette - based features and employing KNN or SVM classifier

This paper presents a new algorithm for human action recognition in videos. This algorithm is based on a combination of two different feature types extracted from Aligned Motion Images (AMIs). The AMI is a method for capturing the motion of all frames in a human action video in one image. The first feature is a contourbased type and is employed to grasp boundary details of the AMI. It relies on the 1st and 2nd discrete time differential of the chorddistance signature feature, so it is called Derivatives of ChordDistance Signature (DCDS). The second feature is a silhouette-based type that is used to capture regional appearance details. It catches most of the visual components for the AMI using a Histogram of Oriented Gradients (HOG) feature. Combining both features creates a complementary feature vector that makes it possible to obtain an optimal correct recognition rate of 100%. For the classification, the algorithm is utilized two different classifiers: K-Nearest-Neighbor (KNN) and Support Vector Machine (SVM). The KNN is based on the 1st norm distance and achieves slightly better results than this obtained by SVM. The performance of the algorithm is tested through six experiments. Three experiments for the KNN classifier and others for the SVM. For each classifier, three experiments conducted to determine the effectiveness of each feature separately and when combined. The experimental results demonstrate the potential power of this algorithm and its promising success in human action recognition in videos. Keywords—Contour-based, human action recognition, video recognition, silhouette-based.