A SSIM-Based Approach for Finding Similar Facial Expressions

Abhinav Dhall, Akshay Asthana, Roland Goecke

Research output: A Conference proceeding or a Chapter in BookConference contribution

6 Citations (Scopus)

Abstract

There are various scenarios where finding the most similar expression is the requirement rather than classifying one into discrete, pre-defined classes, for example, for facial expression transfer and facial expression based automatic album generation. This paper proposes a novel method for finding the most similar facial expression. Instead of the regular L2 norm distance, we investigate the use of the Structural SIMilarity (SSIM) metric for similarity comparison as a distance metric in a nearest neighbour unsupervised algorithm. The feature vectors are generated using Active Appearance Models (AAM). We also demonstrate how this technique can be extended and used for finding corresponding facial expression images across two or more subjects, which is useful in applications such as facial animation and automatic expression transfer. Person-independent facial expression performance results are shown on the Multi-PIE, FEEDTUM and AVOZES databases. We also compare the performance of the SSIM metric versus other distance metrics in a nearest neighbour search for finding the most similar facial expression to a given image
Original languageEnglish
Title of host publication2011 IEEE International Conference on Automatic Face Gesture Recognition and Workshop
EditorsKevin Bowyer, Marian Bartlett, Rainer Stiefelhagen
Place of PublicationUSA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages815-820
Number of pages6
ISBN (Electronic)9781424491414
ISBN (Print)9781424491407
DOIs
Publication statusPublished - 2011
Event 2011 IEEE International Conference on Automatic Face & Gesture Recognition and Workshops (FG 2011) - Santa Barbara, Santa Barbara, United States
Duration: 21 Mar 201125 Mar 2011

Conference

Conference 2011 IEEE International Conference on Automatic Face & Gesture Recognition and Workshops (FG 2011)
CountryUnited States
CitySanta Barbara
Period21/03/1125/03/11

Fingerprint

Animation
Nearest neighbor search

Cite this

Dhall, A., Asthana, A., & Goecke, R. (2011). A SSIM-Based Approach for Finding Similar Facial Expressions. In K. Bowyer, M. Bartlett, & R. Stiefelhagen (Eds.), 2011 IEEE International Conference on Automatic Face Gesture Recognition and Workshop (pp. 815-820). USA: IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/FG.2011.5771354
Dhall, Abhinav ; Asthana, Akshay ; Goecke, Roland. / A SSIM-Based Approach for Finding Similar Facial Expressions. 2011 IEEE International Conference on Automatic Face Gesture Recognition and Workshop. editor / Kevin Bowyer ; Marian Bartlett ; Rainer Stiefelhagen. USA : IEEE, Institute of Electrical and Electronics Engineers, 2011. pp. 815-820
@inproceedings{bf98aa5299694c8c846f5e426555db99,
title = "A SSIM-Based Approach for Finding Similar Facial Expressions",
abstract = "There are various scenarios where finding the most similar expression is the requirement rather than classifying one into discrete, pre-defined classes, for example, for facial expression transfer and facial expression based automatic album generation. This paper proposes a novel method for finding the most similar facial expression. Instead of the regular L2 norm distance, we investigate the use of the Structural SIMilarity (SSIM) metric for similarity comparison as a distance metric in a nearest neighbour unsupervised algorithm. The feature vectors are generated using Active Appearance Models (AAM). We also demonstrate how this technique can be extended and used for finding corresponding facial expression images across two or more subjects, which is useful in applications such as facial animation and automatic expression transfer. Person-independent facial expression performance results are shown on the Multi-PIE, FEEDTUM and AVOZES databases. We also compare the performance of the SSIM metric versus other distance metrics in a nearest neighbour search for finding the most similar facial expression to a given image",
keywords = "Facial expression recognition, SSIM",
author = "Abhinav Dhall and Akshay Asthana and Roland Goecke",
year = "2011",
doi = "10.1109/FG.2011.5771354",
language = "English",
isbn = "9781424491407",
pages = "815--820",
editor = "Kevin Bowyer and Marian Bartlett and Rainer Stiefelhagen",
booktitle = "2011 IEEE International Conference on Automatic Face Gesture Recognition and Workshop",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
address = "United States",

}

Dhall, A, Asthana, A & Goecke, R 2011, A SSIM-Based Approach for Finding Similar Facial Expressions. in K Bowyer, M Bartlett & R Stiefelhagen (eds), 2011 IEEE International Conference on Automatic Face Gesture Recognition and Workshop. IEEE, Institute of Electrical and Electronics Engineers, USA, pp. 815-820, 2011 IEEE International Conference on Automatic Face & Gesture Recognition and Workshops (FG 2011), Santa Barbara, United States, 21/03/11. https://doi.org/10.1109/FG.2011.5771354

A SSIM-Based Approach for Finding Similar Facial Expressions. / Dhall, Abhinav; Asthana, Akshay; Goecke, Roland.

2011 IEEE International Conference on Automatic Face Gesture Recognition and Workshop. ed. / Kevin Bowyer; Marian Bartlett; Rainer Stiefelhagen. USA : IEEE, Institute of Electrical and Electronics Engineers, 2011. p. 815-820.

Research output: A Conference proceeding or a Chapter in BookConference contribution

TY - GEN

T1 - A SSIM-Based Approach for Finding Similar Facial Expressions

AU - Dhall, Abhinav

AU - Asthana, Akshay

AU - Goecke, Roland

PY - 2011

Y1 - 2011

N2 - There are various scenarios where finding the most similar expression is the requirement rather than classifying one into discrete, pre-defined classes, for example, for facial expression transfer and facial expression based automatic album generation. This paper proposes a novel method for finding the most similar facial expression. Instead of the regular L2 norm distance, we investigate the use of the Structural SIMilarity (SSIM) metric for similarity comparison as a distance metric in a nearest neighbour unsupervised algorithm. The feature vectors are generated using Active Appearance Models (AAM). We also demonstrate how this technique can be extended and used for finding corresponding facial expression images across two or more subjects, which is useful in applications such as facial animation and automatic expression transfer. Person-independent facial expression performance results are shown on the Multi-PIE, FEEDTUM and AVOZES databases. We also compare the performance of the SSIM metric versus other distance metrics in a nearest neighbour search for finding the most similar facial expression to a given image

AB - There are various scenarios where finding the most similar expression is the requirement rather than classifying one into discrete, pre-defined classes, for example, for facial expression transfer and facial expression based automatic album generation. This paper proposes a novel method for finding the most similar facial expression. Instead of the regular L2 norm distance, we investigate the use of the Structural SIMilarity (SSIM) metric for similarity comparison as a distance metric in a nearest neighbour unsupervised algorithm. The feature vectors are generated using Active Appearance Models (AAM). We also demonstrate how this technique can be extended and used for finding corresponding facial expression images across two or more subjects, which is useful in applications such as facial animation and automatic expression transfer. Person-independent facial expression performance results are shown on the Multi-PIE, FEEDTUM and AVOZES databases. We also compare the performance of the SSIM metric versus other distance metrics in a nearest neighbour search for finding the most similar facial expression to a given image

KW - Facial expression recognition

KW - SSIM

U2 - 10.1109/FG.2011.5771354

DO - 10.1109/FG.2011.5771354

M3 - Conference contribution

SN - 9781424491407

SP - 815

EP - 820

BT - 2011 IEEE International Conference on Automatic Face Gesture Recognition and Workshop

A2 - Bowyer, Kevin

A2 - Bartlett, Marian

A2 - Stiefelhagen, Rainer

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - USA

ER -

Dhall A, Asthana A, Goecke R. A SSIM-Based Approach for Finding Similar Facial Expressions. In Bowyer K, Bartlett M, Stiefelhagen R, editors, 2011 IEEE International Conference on Automatic Face Gesture Recognition and Workshop. USA: IEEE, Institute of Electrical and Electronics Engineers. 2011. p. 815-820 https://doi.org/10.1109/FG.2011.5771354