Finite State Machines in Movie Scene Classification
Yun Zhai, Zeeshan Rasheed, Mubarak A. Shah · 2004
In this paper, we address the problem of the scene classifications in feature films and propose a robust framework for the stated problem. The framework utilizes the structural information of the movie scenes rather than analyzing the global low level feature values. We propose and demonstrate that the Finite State Machines (FSM) are suitable for classifying the movie scenes into three categories: conversation, explosion/gunfire and suspense. Three major characteristics of motion pictures, motion, color and audio, are used in our approach. The transitions of the FSMs are determined by the mid-level features of each shot in the scene. Our FSMs have been experimented on a large set of data with both positive and negative examples and produces impressive results.