A project on emotion recognition using various databases
I tried using Machine Learning algorithms to classify human emotions into one of 7 categories: happiness, sadness, disgust, anger, fear, surprise and neutral.
A comprehensive description of my efforts is available in the "Face Emotion Recognition Project.pdf" file.
All the uploaded files belong to the "Second Try", as described in the pdf mentioned above. The emotion categories in this try were: happy, angry, sad and neutral.
surf_bow.m is the code for extracting SURF+BoW features and training the categoryClassifier (SVM with Linear Kernel). It achieved 100% accuracy on the training set (this can be verified from confMatrix.mat) and 83% accuracy on the validation set (this can be verified from confMatrix_val.mat).
The GUI.m file is a GUI for demonstrating the outcome of this project on test images, that can be obtained via webcam capture and upload.
Files for the First, Third, Fourth and Fifth Try are available upon request.