PROJECT TITLE :

Smart Trailer : Automatic generation of movie trailer using only subtitles - 2018

ABSTRACT:

With the large growth rate in user-generated videos, it is changing into increasingly important to be able to navigate them efficiently. Video summarization is taken into account a promising approach for efficacious realization of video content through Identifying and picking out descriptive frames of the video. In this Project, we have a tendency to propose an adaptive framework known as Smart-Trailer (S-Trailer) to automate the method of making an online trailer for any movie primarily based solely on its subtitle. The language used in the subtitle is English. The framework analyzes the movie subtitle file to extract relevant textual options that are used to classify the movie into its corresponding genre(s). Initial experimentation resulted in generating genre-classification corpus. The generated corpus is tested against real movies dataset and showed high classification accuracy rate (0.eighty nine) in classifying movies into their corresponding genre(s). The proposed system came back automated trailers that contain on average forty seven% accuracy in terms of recalling scenes appeared on the original movie trailer for different movie genres. Currently, we have a tendency to employ deep learning techniques to captures user behaviors and opinions in order to adapt our system to supply users with relevant video scenes recommendations that match their preferences.