Literature Review: Performance Analysis of CNN, LBP, and Haar Cascade using FER-2013 for Facial Emotion Recognition

Fahar Rafif Arganto
Daffa Aly Meganendra

Journal of Computation Physics and Earth Science
Vol 3 No 2 (2023): Journal of Computation Physics and Earth Science

The rapid progress in artificial intelligence is transforming how humans and computers interact, with facial expressions being key markers of human emotions. Since facial expressions change dynamically during communication, they offer insights into emotional states and have attracted significant research interest. However, detecting emotions through facial recognition is challenging due to individual differences in expressions, varied lighting conditions, and different facial orientations. These challenges highlight the need for models that can effectively address these issues to improve detection accuracy. This literature review explores several commonly used algorithms for emotion detection via facial recognition, including Convolutional Neural Networks (CNN), Haar Cascade, and Local Binary Pattern (LBP), with the FER2013 dataset serving as the basis for analysis.