This dataset is developed by Dewi Yanti Liliana as part of doctoral research project at Faculty of Computer Science, Universitas Indonesia, supervised by Professor T. Basaruddin, Ph.D. The dataset consists of 19 classes of emotions, such as happy, sad, angry, etc., demonstrated by six male and nine female subjects. There are 6 basic emotions, 12 mixed emotions, and neutral facial expression in video and image format. All participants are Indonesian, aged from 17 to 32 years old, from various ethnicities includes pure and mixed of Javanese, Bataknese, Sundanese, Minang, and Manadonese.
To get access to this dataset, please register for an account here. After registering, please provide us with supplemental documents to help us process your request easier. In these documents included: a filled dataset request form, and other documents such as letter of recommendations/supports. Kindly send these documents to us at dewiyanti.liliana@tik.pnj.ac.id to help us approve your request.
Further details regarding this dataset can be found at:
Dewi Yanti Liliana, T. Basaruddin, Imelda Ika Dian Oriza. 2018. The Indonesian Mixed Emotion Dataset (IMED): A Facial Expression Dataset for Mixed Emotion Recognition, in Proceeding of the 2018 International Conference on Artificial Intelligence and Virtual Reality (AIVR 2018). ACM, New York, NY, USA, 56-60. DOI: https://doi.org/10.1145/3293663.3293671
Please cite this reference if you intended to use this dataset in your research.