Facial Expression Recognition
I implemented two techniques for auto-FER. First, I retrained AlexNet, used transfer learning for classification(Transfer Learning). Second, I used AlexNet for feature extraction and cascaded it with an SVM for classification. I achieved 93% accuracy with AlexNet and 95% with AlexNet-SVM cascade which is comparable with the contemporary methods that give 96-98%. Data augmentation and training with larger dataset can improve the accuracy with deep learning I used JAFFE Data Set to train my both models.
I am a Researcher with expertise in machine learning, Deep Learning signal processing and image processing. I have excellent programming skills. I have good grip on MATLAB, Python and C/C++. But the main thing about me is my capability to learn new things fast and work in different environment with people from different countries. Client satisfaction is my 1st priority. - 30 days error free service - Continued support after the delivery of final product - 100 % satisfaction guaranteed