Skip to content

Latest commit

 

History

History
5 lines (5 loc) · 508 Bytes

README.md

File metadata and controls

5 lines (5 loc) · 508 Bytes

FER

    Implemented DCNN (Deep Convolutional Neural Network) approach for classifying the Facial Emotion Recognition (FER) dataset using VGG13 as the base architecture. 
    This approach was based on a research paper by Microsoft Research for the FER+ dataset. 
    The results obtained were further enhanced by applying Sobel and Laplacian filter to the images to detect edges and feeding it into the model. 
    This work was done as a part of my research internship at IISC. Bangalore.