<![CDATA[The basic human emotions have been widely investigated cross-culturally, one of them by using facial expressions. Through the micro expression on the face can be known even one's psychological emotions. Basic expression is universal means that the child or the blind can know or form a basic expression. Micro expression is an expression that appears subtle and unconscious. Micro expression is very difficult or even can not be hidden. This research uses Local Binary Pattern (LBP) method to get features of facial micro expression and classification using K-Nearest Neighbor (K-NN) method to determine the emotion of micro expression. The result of k-value determination test on K-NN classification method shows that when k value 5 and 7 is able to recognize emotion based on micro expression with 56,03% accuracy. The result of determination test of R value and P value on LBP method showed an increase of accuracy in emotional recognition to 63,83%. The test results on the dimension of the image shows that the dimension of the image that produces the best accuracy is 200×200 pixels with an accuracy value of 63.83%. The observation using distance method on K-NN classification shows that Manhattan distance calculation method can increase accuracy in emotional recognition to 70.21%.]]>
Copyrights © 2018
