ABSTRACT
In today's media environment, there is an increasing demand for a method to technically analyze moving image. In the field of film, which consists of vast amounts of data, an efficient method and structure for analyzing moving image information is indispensable. This study presented short segmentation and film analysis methods and results, focusing on sequences through Barycenter algorithms and machine learning methodologies, in Dziga Vertov's "Man with a Movie Camera," a director representing the silent film era. The existing proposed machine learning methodology simultaneously utilizes the Barycenter algorithm method in short segmentation due to its limited accuracy, although the time required for short segmentation is small. The Barycenter algorithm is a method of finding the center of gravity in the image by brightness and saturation, and has high short segmentation accuracy compared to the machine learning methodology through center movement. This proved that the method of using the Barycenter algorithm presented in this study has higher accuracy than the existing method. This study aims to contribute as a criticism tool based on quantitative indicators of film as well as to improve understanding and characterization of film.