FACIAL EXPRESSION RECOGNITION SYSTEM USING

WEIGHT-BASED APPROACH

Srinivasa K G, Inchara Shivalingaiah, Lisa Gracias, and Nischit Ranganath

M.S Ramaiah Institute of Technology, India

http://www.msrit.edu

Introduction:

This paper present a method to identify the facial expressions of a user by processing images taken from a webcam. This is done by passing the image through 3 stages -face detection, feature extraction, and expression recognition. Face detection is accomplished by implementing the concept of Haar-like features to prioritize reduction in detection time over accuracy.

Problems:

• Presence or absence of structural components like facial hair, glasses, etc., affects the accuracy of detection.
• The orientation of the face affects the feature detection. The face must not be tilted, and must be directed straight at the camera.
• Webcam images captured under improper lighting.

Approach:

Facial features are extracted from their respective regions of interest using Gabor filters and classified based on facial ratios and symmetry. They plotted a minimal number of facial points (12 points) and compared the positions of these points on the neutral expression image and the current expression image. This allowed them to recognize 8 expressions based on the facial movements made as opposed to identifying just the 6 basic expressions as done by research papers previously.

Strength:

They were able to reach an accuracy level of approximately 92% for expression recognition when tested with the JAFFE database. This is a considerably high performance when taking into account the simplicity of the algorithm involved.

Functional Requirements:

• Face localization: To detect the face present in an image taken from the webcam.
• Region of Interest Detection: To divide the face into regions of interest for feature extraction in each region.
• Feature Extraction: To detect the features present in each region of interest.
• Feature Classification: To classify the features detected based on their relative and absolute distances on the face.
• Expression Recognition: To identify the expression made based on the feature movements.

Method:

• Use 3 algorithms to Face Detection, Feature Extraction & Expression Recognition.
•  Functional architecture
•  Face Detection: The input image is scanned across location and scale. At each location, an independent decision is made regarding the presence of a face.
•  Region of Interest (ROI) Detection: Determine the ROI for each point, that is, to define a large region which contains the point that we want to detect.
• Feature Extraction: Predict whether the current point represents a certain facial point or not.
• Feature Classification: Detect correct feature for particular feature point.
•  Expression Recognition: A database of 50 people making 8 expressions

Future work:

 Investigate effects of using a reduced number of features for classification. Also, we plan to conduct extensive experimental studies using other publicly available face databases.

Download Research Paper:

https://drive.google.com/file/d/0B3VmCeqDC7SDSzZxMXQzLVJieFE/view?usp=sharing