eyeball_tracking_own.py

import cv2
import dlib
import numpy as np

# 用來顯示的函示庫
import matplotlib.pyplot as plt
import matplotlib.image as mpimg 

# init part
FACE_CASCADE = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')
EYES_CASCADE = cv2.CascadeClassifier('haarcascade_eye_tree_eyeglasses.xml')
detector_params = cv2.SimpleBlobDetector_Params()
detector_params.filterByArea = True
detector_params.maxArea = 1500
detector = cv2.SimpleBlobDetector_create(detector_params)

# 建立人臉細節偵測
predictor = dlib.shape_predictor('shape_predictor_68_face_landmarks.dat')

# 臉部偵測
def detect_faces(img, cascade):
    gray_frame = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
    coords = cascade.detectMultiScale(gray_frame, 1.3, 5)
    if len(coords) > 1:
        biggest = (0, 0, 0, 0)
        for i in coords:
            if i[3] > biggest[3]:
                biggest = i
        biggest = np.array([i], np.int32)
    elif len(coords) == 1:
        biggest = coords
    else:
        return None
    for (x, y, w, h) in biggest:
        frame = img[y:y + h, x:x + w]
    return frame


def detect_eyes(img, cascade):
    gray_frame = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
    eyes = cascade.detectMultiScale(gray_frame, 1.3, 5)  # detect eyes
    width = np.size(img, 1)  # get face frame width
    height = np.size(img, 0)  # get face frame height
    left_eye = None
    right_eye = None
    for (x, y, w, h) in eyes:
        if y > height / 2:
            pass
        eyecenter = x + w / 2  # get the eye center
        if eyecenter < width * 0.5:
            left_eye = img[y:y + h, x:x + w]
        else:
            right_eye = img[y:y + h, x:x + w]
    
       
    return left_eye, right_eye


def cut_eyebrows(img):
    height, width = img.shape[:2]
    eyebrow_h = int(height / 4)
    img = img[eyebrow_h:height, 0:width]  # cut eyebrows out (15 px)

    return img


def blob_process(img, threshold, detector):
    gray_frame = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
    _, img = cv2.threshold(gray_frame, threshold, 255, cv2.THRESH_BINARY)
    img = cv2.erode(img, None, iterations=2)
    img = cv2.dilate(img, None, iterations=4)
    img = cv2.medianBlur(img, 3)
    keypoints = detector.detect(img)
    print(keypoints)
    return keypoints


def nothing(x):
    pass

# 將特徵點的座標給儲存下來
def shape_to_np(shape, dtype = "int"):
	# initialize the list of (x, y)-coordinates
	coords = np.zeros((68, 2), dtype = dtype)
	# loop over the 68 facial landmarks and convert them
	# to a 2-tuple of (x, y)-coordinates
	for i in range(0, 68):
		coords[i] = (shape.part(i).x, shape.part(i).y)
	# return the list of (x, y)-coordinates
	return coords


def main():
    cap = cv2.VideoCapture(0)
    cv2.namedWindow('image')
    cv2.createTrackbar('threshold', 'image', 0, 255, nothing)


    while True:
        _, frame = cap.read()
        face_frame = detect_faces(frame, FACE_CASCADE)
        if face_frame is not None:
            eyes = detect_eyes(face_frame, EYES_CASCADE)


            for eye in eyes:

                # 判斷是否有找到眼睛
                if eye is not None:
                    threshold = r = cv2.getTrackbarPos('threshold', 'image')
                    eye = cut_eyebrows(eye)
                    keypoints = blob_process(eye, threshold, detector)
                    eye = cv2.drawKeypoints(eye, keypoints, eye, (0, 0, 255), cv2.DRAW_MATCHES_FLAGS_DRAW_RICH_KEYPOINTS)


        cv2.imshow('image', frame)

        # 離開迴圈，關閉攝影機
        if cv2.waitKey(1) & 0xFF == ord('q'):
            break


    cap.release()
    cv2.destroyAllWindows()


if __name__ == "__main__":
    main()