A Method for Facial Emotion Recognition Based on Interest Points


Current facial recognition techniques allow to automatically determine human emotions through a digital image of the face. The present study employs interest points as landmarks in facial images affected by some emotion and compares their positions with those of a neutral expression. We seek to establish a relationship between the obtained results and the ones proposed by Paul Ekman's FACS (Facial Action Coding System) tool to determine the viability of an emotion recognition algorithm as well as some possible guidelines for its implementation.



Machine learning algorithms

Software And Hardware

• Hardware: Processor: i3 ,i5 RAM: 4GB Hard disk: 16 GB • Software: operating System : Windws2000/XP/7/8/10 Anaconda,jupyter,spyder,flask Frontend :-python Backend:- MYSQL