Facial Keypoints Detection with Convolution Neural Networks

    Author Name(s)

    Austin Fisher
    Alexander Slankard
    Maxwell Deleon
    Mathew Zekoll

    Faculty Advisor(s)

    Alona Kryshchenko


    Facial Keypoints Detection is an interesting, yet complex problem that presents itself in the fields of both computer vision and machine learning. In this project, we attempt to determine the coordinates of facial keypoints by utilizing a convolution neural network (CNN) for our predictive modeling. The models are trained and tested on a dataset containing images stored in a 96×96 resolution with 8-bit grayscale pixel values. We explore different types of error estimation utilizing a subset of our data with known facial keypoints to determine the accuracy, precision and mean squared error of our regression models.



    Leave a Reply

    Your email address will not be published. Required fields are marked *