Fused Convolutional Neural Network for Facial Expression Recognition
M.K. Mohd Fitri Alif1, A.R. Syafeeza2
1M.K. Mohd Fitri Alif, School of Electrical Engineering, Faculty of Engineering, Universiti Teknologi Malaysia, Johor Bahru, Johor, Malaysia.
2A.R. Syafeeza, Faculty of Electronic Engineering and Computer Engineering, Universiti Teknikal Malaysia Melaka, Hang Tuah Jaya, Durian Tunggal, Melaka, Malaysia.
Manuscript received on 09 December 2019 | Revised Manuscript received on 23 December 2019 | Manuscript Published on 31 December 2019 | PP: 528-532 | Volume-8 Issue-12S2 October 2019 | Retrieval Number: L109810812S219/2019©BEIESP | DOI: 10.35940/ijitee.L1098.10812S219
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open-access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: This study aims to find the optimal learning algorithm parameter, model and connection, initialization weight and normalization method using fused Convolutional Neural Network (CNN) for facial expression recognition. The best model and parameters are identified using a ten-fold cross validation method. By determining these ideal elements, a superior accuracy can potentially be achieved. CNN was utilized to a group of seven emotions from various facial expressions, namely, happy, sad, angry, surprise, disgust, fear and neutral. The four layer CNN configuration was prepared with the JAFFE dataset, and yielded an overall accuracy of 83.72%. The outcome demonstrates that the fused CNN with the mentioned aims can generate higher accuracy with a smaller network compared to related models.
Keywords: Deep Learning, Emotion Recognition, Facial Expression Recognition, Fused Convolutional Neural Network, Stochastic Diagonal Levenberg Marquadt.
Scope of the Article: Pattern Recognition