The Storyteller’S Aide: An Index Of Compositional Properties In Cinema

Justin Smith

School Name

Governor's School for Science and Math

Grade Level

12th Grade

Presentation Topic

Math and Computer Science

Presentation Type

Mentored

Mentor

Mentor: Dr. Bares; Department of Computer Science, College of Charleston

Abstract

This project aims to create a program that can effectively instruct novice filmmakers on the compositional properties best suited for a particular scene, the effect one particular composition may have on the viewer, and different ways compositions can be used to convey desired messages to the audience. Current filmmaking programs lack the capability to understand why a particular composition should be used over another. Instead, programs generally considered to be the “state-of-the-art” in pre-professional filmmaking, such as Adobe Premiere, Final Cut Pro, and iMovie, are only able to make suggestions based on the composition, not the impact the composition can make with the audience. This program gains its unique characteristics from the use of a K-means clustering algorithm and a hand-built indexing structure, which served as the basis for classification of shots based on compositional properties and then grouping them according to high-level storytelling goals, which allows the program to make suggestions with an intuitive knowledge of the emotions of the viewer. The project’s goal is to develop a program that not only is able to make intelligent suggestions based on common storytelling goals and desired emotional impacts, but to also be highly adaptable to new influxes of techniques and composition styles within the film industry. The intelligent assistant will provide novice filmmakers with an effective video and shot editing tool that will not be limited to one platform.

Location

Owens 207

Start Date

4-16-2016 11:45 AM

COinS
 
Apr 16th, 11:45 AM

The Storyteller’S Aide: An Index Of Compositional Properties In Cinema

Owens 207

This project aims to create a program that can effectively instruct novice filmmakers on the compositional properties best suited for a particular scene, the effect one particular composition may have on the viewer, and different ways compositions can be used to convey desired messages to the audience. Current filmmaking programs lack the capability to understand why a particular composition should be used over another. Instead, programs generally considered to be the “state-of-the-art” in pre-professional filmmaking, such as Adobe Premiere, Final Cut Pro, and iMovie, are only able to make suggestions based on the composition, not the impact the composition can make with the audience. This program gains its unique characteristics from the use of a K-means clustering algorithm and a hand-built indexing structure, which served as the basis for classification of shots based on compositional properties and then grouping them according to high-level storytelling goals, which allows the program to make suggestions with an intuitive knowledge of the emotions of the viewer. The project’s goal is to develop a program that not only is able to make intelligent suggestions based on common storytelling goals and desired emotional impacts, but to also be highly adaptable to new influxes of techniques and composition styles within the film industry. The intelligent assistant will provide novice filmmakers with an effective video and shot editing tool that will not be limited to one platform.