VIDEO KEY FRAME DETECTION BASED ON THE RESTRICTED BOLTZMANN MACHINE

In this paper we present a new method for key frame detection. Our approach is based on a well-known algorithm of the Restricted Boltzmann Machine (RBM), which is a pivotal step in our method. The frames are compared to the RBM matcher, which allows one to search for key frame in the video sequence. The Restricted Boltzmann Machine is one of sophisticated types of neural networks, which can process the probability distribution, and is applied to filtering image recognition and modelling. The learning procedure is based on the matrix description of RBM, where the learning samples are grouped into packages, and represented as matrices. Our research confirms a potential usefulness for video key frame detection. The proposed method provides better results for professional and high-resolution videos. The simulations we conducted proved the effectiveness of our approach. The algorithm requires only one input parameter.