The Extended Cohn-Kanade Dataset (CK+): A complete dataset for action unit and emotion-specified expression

TLDR

The Cohn‑Kanade database, released in 2000, is widely used for facial expression research but suffers from unvalidated emotion labels, a lack of common performance metrics, and no standard protocols, making comparisons and meta‑analyses difficult. To remedy these issues, the authors present the Extended Cohn‑Kanade (CK+) database. CK+ enlarges the original set by 22 % more sequences and 27 % more subjects, provides fully FACS‑coded target expressions, validated emotion labels, and adds non‑posed smile sequences with associated metadata. Baseline experiments using Active Appearance Models and a linear SVM with leave‑one‑out cross‑validation demonstrate AU and emotion detection on posed data, and the dataset, labels, images, and landmarks will be released in July 2010.

Abstract

In 2000, the Cohn-Kanade (CK) database was released for the purpose of promoting research into automatically detecting individual facial expressions. Since then, the CK database has become one of the most widely used test-beds for algorithm development and evaluation. During this period, three limitations have become apparent: 1) While AU codes are well validated, emotion labels are not, as they refer to what was requested rather than what was actually performed, 2) The lack of a common performance metric against which to evaluate new algorithms, and 3) Standard protocols for common databases have not emerged. As a consequence, the CK database has been used for both AU and emotion detection (even though labels for the latter have not been validated), comparison with benchmark algorithms is missing, and use of random subsets of the original database makes meta-analyses difficult. To address these and other concerns, we present the Extended Cohn-Kanade (CK+) database. The number of sequences is increased by 22% and the number of subjects by 27%. The target expression for each sequence is fully FACS coded and emotion labels have been revised and validated. In addition to this, non-posed sequences for several types of smiles and their associated metadata have been added. We present baseline results using Active Appearance Models (AAMs) and a linear support vector machine (SVM) classifier using a leave-one-out subject cross-validation for both AU and emotion detection for the posed data. The emotion and AU labels, along with the extended image data and tracked landmarks will be made available July 2010.