Only logged in customers who have purchased this product may leave a review.
Facial Expression Recognition Using HoG Features
In this work a comprehensive study of how the HoG, HoB, BO, LBP features could be effectively exploited for facial expression recognition (FER) purposes has been carried out. In order to perform the above mentioned investigation, a procedure, commonly used in FER analysis and equipped with several features, has been used as baseline. Results highlighted
a configuration of HoG and LBP parameters able to fit the specific aspects of facial expressions that allows a high classification performance capable to overcome the performances of using only HoG features.