Real_time facial-landmarks-dlib-opencv-python

Practice with using dlib, imutils package reference(https://www.pyimagesearch.com/2017/04/03/facial-landmarks-dlib-opencv-python/)

The Objectives of a project

Using a webcam, we will get real-time video. so, I will detect facial-landmakrs (detect Eyes, Eyebows, Nose, Mouth, Jawline).

pre-trained Linear SVM object detector specifically for the task of face detect.

Result

image Data <BTS>

Using Methods

face_utils.rect_to_bb(rect) : take a bounding predicted by dlib and convert it , transforms it into 4 tuple of coordinates.

face_utils.shape_to_np(shape) : we cam convert this object to Numpy array.

dlib.face_detector : Histogram of Oriented Gradients + Linear SVM method

Additional

If you want more detailed study go to

https://www.pyimagesearch.com/2017/04/03/facial-landmarks-dlib-opencv-python/

If you want source code

https://github.com/sunjungAn/Opencv_practice/blob/master/Facial%20landmarks%20with%20dlib%2C%20OpenCV%2C%20and%20Python/facial_landmarks.py