Result: FACIAL ANALYSIS METHOD FOR EMOTION RECOGNITION USING LBP OPERATOR.

In terms of interpersonal relationships, emotional expressions are vital to the development and regulation, and to sustain this, there are three examples that facial expressions should be involved in the formation of attachments, regulation, and acceleration or deceleration of aggression. Talking about human beings, the face is the body part that reveals the most information about the person itself. The face can give details about intention and attentiveness, about mood, and, on the other hand, the face is the main path in recognition of a person. In a word, the face is the most distinctive and the most used method in finding a person's identity. It will be implemented a method for basic emotion recognition (happiness, sadness, anger, surprise, disgust, fear, neutral) in pictures with facial expressions will be implemented. The method will start with face detection and face fiducial points localization using DLIB public library. The Local Binary Patterns (LBP) features will be computed in areas of interest on the face and the classification will be done using a support vector machine (SVM). Pictures in which the person has a neutral expression and, respectively, pictures in which the expression is at the apex of the emotion will be used. The method will be tested on a public database containing sequences of images starting from the neutral expression and going to the apex expression for different persons. The classifier will be tested in different scenarios: leave-one-person-out, leave-one-sequence-out, etc. The implementation will be done in Python and it will be used OpenCV, DLIB and LibSVM public libraries. [ABSTRACT FROM AUTHOR]

Copyright of eLearning & Software for Education is the property of Carol I National Defence University and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)