Facial expression recognition by using modified convolutional neural network (mcnn) and modified gabor filter

×

Error message

User warning: The following theme is missing from the file system: journalijdr. For information about how to fix this, see the documentation page. in _drupal_trigger_error_with_delayed_logging() (line 1138 of /home2/journalijdr/public_html/includes/bootstrap.inc).

International Journal of Development Research

Volume: 
7
Article ID: 
11078
8 pages
Research Article

Facial expression recognition by using modified convolutional neural network (mcnn) and modified gabor filter

Lafta Raheem Ali, Dr. Haider Kadhim Homood and Dr. Amer Saleem Elameer

Abstract: 

Facial expression recognition is an important topic in an image processing and pattern recognition. The expressions work as a mirror for what happened in the human mind, enable individuals to understand what their peers feel. This paper suggest develop a system for recognizing facial expressions, modified Gabor filter has been use for feature extraction, then classifying the facial expressions based on these extracted features by using a modified Convolutional Neural Network (MCNN). the results of using MCNN with Modified Gabor was (93%-99%) accuracy rate with very less time for both multi and single face respectively We have gotten a very good result comparing to the other methods in the same fields (PCA and Gabor filter. This results with Extended Cohn Kanade (CK+) and JAFFE Databases.

Download PDF: