3D fuzzy GIST to analyze emotional features in movies

Authors:
Mingu Kwon;Minho Lee
Affiliations:
School of Electronics Engineering and Computer Science, Kyungpook National University, Puk-Gu, Taegu, Korea;School of Electronics Engineering and Computer Science, Kyungpook National University, Puk-Gu, Taegu, Korea
Venue:
IDEAL'12 Proceedings of the 13th international conference on Intelligent Data Engineering and Automated Learning
Year:
2012

Citing 8
Cited 0

Neuro-fuzzy and soft computing: a computational approach to learning and machine intelligence

Neuro-fuzzy and soft computing: a computational approach to learning and machine intelligence
Affective computing

Affective computing
Possibility theory is not fully compositional!: a comment on a short note by H.J. Greenberg

Fuzzy Sets and Systems
Semantics in Visual Information Retrieval

IEEE MultiMedia
Semantic Annotation of Sports Videos

IEEE MultiMedia
Letters: Analysis of positive and negative emotions in natural scene using brain activity and GIST

Neurocomputing
Fuzzy-GIST for emotion recognition in natural scene images

DEVLRN '09 Proceedings of the 2009 IEEE 8th International Conference on Development and Learning
Autonomous emotion development using incremental modified adaptive neuro-fuzzy inference system

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we propose a 3D fuzzy GIST to effectively describe the visual dynamic features related to the emotional characteristics in a movie clip. Unlike the previous fuzzy approaches, which use images, the proposed method employs movie clips and can dynamically extract the features to classify the emotional characteristics in a movie clip. The 3D fuzzy GIST based on 3D tensor data including L*C*H color (L: Lightness, C: Chroma, H: Hue) and orientation information in a movie clip can extract the visual dynamic features related to the emotional characteristics in a movie clip. The extracted visual dynamic features obtained by the proposed 3D fuzzy GIST are used as inputs to an adaptive neuro-fuzzy inference classifier. The classifier is provided with the mean opinion scores as the teaching signals. Experimental results show that the system with the proposed 3D fuzzy GIST feature extractor not only discriminates the positive emotional features from the negative ones but also identifies the changes of emotional features in movie clips successfully.