dlib 配置及使用方法

配置

py3.6+dlib：目前window这么配置不会报错。dlib去官网或者python包网（https://pypi.org/simple/dlib/ ）都能下载，下载到本地，然后pip直接安装就好。

使用

准备工作

dlib之所以能识别脸部关键点是因为他是深度学习模型，在使用前，需要去下载模型：http://dlib.net/files/，看下图，主要是这些模型。

我这里选择shape_predictor_68_face_landmarks.dat.bz2 ，然后解压，能检测出来68个点。下图为关键点的位置

例子 1 

下面为识别一个图片的例子

import cv2
import dlib
 
path = "img/meinv.png"
img = cv2.imread(path)
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
 
#人脸分类器
detector = dlib.get_frontal_face_detector()
# 获取人脸检测器
predictor = dlib.shape_predictor(
    "C:\\Python36\\Lib\\site-packages\\dlib-data\\shape_predictor_68_face_landmarks.dat"
)
 
dets = detector(gray, 1)
for face in dets:
    shape = predictor(img, face)  # 寻找人脸的68个标定点
    # 遍历所有点，打印出其坐标，并圈出来
    for pt in shape.parts():
        pt_pos = (pt.x, pt.y)
        cv2.circle(img, pt_pos, 2, (0, 255, 0), 1)
    cv2.imshow("image", img)
 
cv2.waitKey(0)
cv2.destroyAllWindows()

例子2

这个是活体检测，用的是判断人眼的眨动。

参数的含义看示意图

 

# USAGE
# python detect_blinks.py --shape-predictor shape_predictor_68_face_landmarks.dat --video blink_detection_demo.mp4
# python detect_blinks.py --shape-predictor shape_predictor_68_face_landmarks.dat

# import the necessary packages
from scipy.spatial import distance as dist
from imutils.video import FileVideoStream
from imutils.video import VideoStream
from imutils import face_utils
import numpy as np
import argparse
import imutils
import time
import dlib
import cv2

def eye_aspect_ratio(eye):
	# compute the euclidean distances between the two sets of
	# vertical eye landmarks (x, y)-coordinates 欧氏距离
	A = dist.euclidean(eye[1], eye[5])
	B = dist.euclidean(eye[2], eye[4])

	# compute the euclidean distance between the horizontal
	# eye landmark (x, y)-coordinates
	C = dist.euclidean(eye[0], eye[3])
	'''
		[1]	[2]
	[0]			[3]
		[5]	[4]
	'''
	# compute the eye aspect ratio
	ear = (A + B) / (2.0 * C)

	# return the eye aspect ratio
	return ear



# # 我注释掉的 construct the argument parse and parse the arguments
# ap = argparse.ArgumentParser()
# ap.add_argument("-p", "--shape-predictor", required=True,
# 	help="path to facial landmark predictor")
# ap.add_argument("-v", "--video", type=str, default="",
# 	help="path to input video file")
# args = vars(ap.parse_args())

p = 'shape_predictor_68_face_landmarks.dat'
v = "blink_detection_demo.mp4"

# define two constants, one for the eye aspect ratio to indicate
# blink and then a second constant for the number of consecutive
# frames the eye must be below the threshold
EYE_AR_THRESH = 0.3
EYE_AR_CONSEC_FRAMES = 3

# initialize the frame counters and the total number of blinks
COUNTER = 0
TOTAL = 0

# 初始化dlib's face detector (HOG-based)，然后创建“面部标志预测器”facial landmark predictor
print("[INFO] loading facial landmark predictor...")
detector = dlib.get_frontal_face_detector() # 创建识别器
'''
print("detector:",help(detector))
This object represents a sliding window histogram-of-oriented-gradients based object detector.
此对象表示基于定向梯度的对象检测器的滑动窗口直方图。
'''

# predictor = dlib.shape_predictor(args["shape_predictor"])
predictor = dlib.shape_predictor(p) # 读取训练好的模型
"""
print("predictor",help(predictor))
This object is a tool that takes in an image region containing some 
object and outputs a set of point locations that define the pose of the object. 
The classic example of this is human face pose prediction, where you take 
an image of a human face as input and are expected to identify the locations of 
important facial landmarks such as the corners of the mouth and eyes, tip of the nose, and so forth。
此对象是一个工具，它接受包含某些对象的图像区域，并输出一组定义对象姿势的点位置。
这方面的经典例子是人脸姿势预测，在这里，您可以将人脸的图像作为输入，
并期望识别重要面部标志的位置，如嘴角和眼睛、鼻尖等。
"""

# 分别地抓取人脸的左眼和右眼的坐标 respectively
(lStart, lEnd) = face_utils.FACIAL_LANDMARKS_IDXS["left_eye"]
(rStart, rEnd) = face_utils.FACIAL_LANDMARKS_IDXS["right_eye"]
# face_utils.FACIAL_LANDMARKS_IDXS:Dictionary that remembers insertion order
# 开始读取视频流
print("[INFO] starting video stream thread...")
# vs = FileVideoStream(args["video"]).start()
vs = FileVideoStream(v).start()  # 开始读取
fileStream = True
# vs = VideoStream(src=0).start()
# vs = VideoStream(usePiCamera=True).start()
# fileStream = False
time.sleep(1.0)



# 从视频流循环帧
while True:
	# if this is a file video stream, then we need to check if
	# there any more frames left in the buffer to process
	if fileStream and not vs.more():  # vs.more() 当vs存在时返回True，否则返回False
		break

	# grab the frame from the threaded video file stream, resize
	# it, and convert it to grayscale
	# channels)
	frame = vs.read() # 读取一针
	frame = imutils.resize(frame, width=450) # 设置宽度  ·450
	gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)

	# 创建灰度图识别器  进行识别加快速度
	rects = detector(gray, 0)

	# loop over the face detections
	for rect in rects:
		# determine the facial landmarks for the face region, then
		# convert the facial landmark (x, y)-coordinates to a NumPy
		# array
		shape = predictor(gray, rect) # 进行预测 返回值包括眼睛鼻子嘴的坐标
		shape = face_utils.shape_to_np(shape)

		# extract the left and right eye coordinates, then use the
		# coordinates to compute the eye aspect ratio for both eyes
		leftEye = shape[lStart:lEnd]
		rightEye = shape[rStart:rEnd]
		leftEAR = eye_aspect_ratio(leftEye)
		rightEAR = eye_aspect_ratio(rightEye)

		# average the eye aspect ratio together for both eyes
		ear = (leftEAR + rightEAR) / 2.0

		# compute the convex hull for the left and right eye, then
		# visualize each of the eyes
		leftEyeHull = cv2.convexHull(leftEye)
		rightEyeHull = cv2.convexHull(rightEye)
		cv2.drawContours(frame, [leftEyeHull], -1, (0, 255, 0), 1)
		cv2.drawContours(frame, [rightEyeHull], -1, (0, 255, 0), 1)

		# check to see if the eye aspect ratio is below the blink
		# threshold, and if so, increment the blink frame counter
		if ear < EYE_AR_THRESH:
			COUNTER += 1

		# otherwise, the eye aspect ratio is not below the blink
		# threshold
		else:
			# if the eyes were closed for a sufficient number of
			# then increment the total number of blinks
			if COUNTER >= EYE_AR_CONSEC_FRAMES:
				TOTAL += 1

			# reset the eye frame counter
			COUNTER = 0

		# draw the total number of blinks on the frame along with
		# the computed eye aspect ratio for the frame
		cv2.putText(frame, "Blinks: {}".format(TOTAL), (10, 30),
			cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 0, 255), 2)
		cv2.putText(frame, "EAR: {:.2f}".format(ear), (300, 30),
			cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 0, 255), 2)
 
	# show the frame
	cv2.imshow("Frame", frame)
	key = cv2.waitKey(1) & 0xFF
 
	# if the `q` key was pressed, break from the loop
	if key == ord("q"):
		break

# do a bit of cleanup
cv2.destroyAllWindows()
vs.stop()

同理你也可以判断嘴巴的张合。不过用到的公司需要修改下。要用到52-58-49-55，63--67--61--65。公式见下面，里面考虑了一个问题，就是后唇和薄唇带的来的闭合不明显。

 

例子3 

由于某些原因不停工这个代码，说出自己想法。抖音上换脸的玩法都知道霸，可以通过关键点来实现，有电脑都。

例子4

某游戏可以通过拍照人脸来捏游戏人物角色的脸，也是用关键点实现的。