Content-based video recognition technique using a nonlinear metric

This work focuses on the videoclip recognition task. The proposed video recognition approach represents a process composed of two parts: the feature extraction operation and the classification of the obtained video feature vectors. We provide a way to define the similarity between movies. In the featuring stage each clip is characterized by the graphical content, expressed by some feature vectors, of its keyframes. Shot detection and keyframe extraction techniques are also provided. We then propose a special nonlinear metric which is able to compare video feature vectors represented as matrices having different dimensions, and use it in the classification process