In this project, knowledge of computer vision techniques and deep learning are combined to build and end-to-end facial keypoint recognition system. Facial keypoints include points around the eyes, nose, and mouth on any face and are used in many applications, from facial tracking to emotion recognition. The complete algo is able to take in any image containing faces and identify the location of each face and their facial keypoints, as shown below.
This also containes optional exercises that extends this project so that it works on video and allows to implement fun face filters in real-time!
-
You should have python and opnen cv installed other than deep learning libraries. if not then follow the instruction here to setup environment.
-
Look in this repo in the subdirectory
data/
; in this folder, you'll find zipped testing data calledtest.zip
. Unzip this file and place it in this same location. You should then have a file calledtraining.csv
in the data folder. You may delete the zip file. -
Download the Kaggle training dataset called
training.zip
. Unzip the file and place it in the samedata/
subdirectory as the test data. You should now have two files in there includingtraining.csv
. -
Open the notebook and follow the instructions.
jupyter notebook CV_project.ipynb