Recognition of Facial Expression Using Eigenvector Based Distributed Features and Euclidean Distance Based Decision Making Technique
This work addresses facial expression recognition for applications like human-computer interaction, but it appears incremental as it builds on established Eigenvector and Euclidean distance methods without major innovations.
The paper tackled facial expression recognition by using an Eigenvector-based system to extract features from cropped image portions and applying Euclidean distance for similarity matching, achieving recognition through minimum distance calculations.
In this paper, an Eigenvector based system has been presented to recognize facial expressions from digital facial images. In the approach, firstly the images were acquired and cropping of five significant portions from the image was performed to extract and store the Eigenvectors specific to the expressions. The Eigenvectors for the test images were also computed, and finally the input facial image was recognized when similarity was obtained by calculating the minimum Euclidean distance between the test image and the different expressions.