Python影像辨識筆記(一):使用Open CV辨識圖片及影片中的人臉

Yanwei Liu
5 min readApr 25, 2019
以電影海報為例

圖片人臉

安裝模組

pip install opencv-python

偵測人臉

import cv2# 載入分類器
face_cascade = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')
# 讀取圖片
img = cv2.imread('a.jpg')
# 轉成灰階圖片
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# 偵測臉部faces = face_cascade.detectMultiScale(
gray,
scaleFactor=1.08,
minNeighbors=5,
minSize=(32, 32))
# 繪製人臉部份的方框
for (x, y, w, h) in faces:
cv2.rectangle(img, (x, y), (x + w, y + h), (0, 255, 0), 2)
#(0, 255, 0)欄位可以變更方框顏色(Blue,Green,Red)# 顯示成果
cv2.namedWindow('img', cv2.WINDOW_NORMAL) #正常視窗大小
cv2.imshow('img', img) #秀出圖片
cv2.imwrite( "result.jpg", img ) #保存圖片
cv2.waitKey(0) #等待按下任一按鍵
cv2.destroyAllWindows() #關閉視窗
  • scaleFactor: Parameter specifying how much the image size is reduced at each image scale. Increasing it leads to faster detection with the risk of missing some objects, whereas a small value might sometimes be too thorough.
  • minNeighbors: Parameter specifying how many neighbors each candidate rectangle should have to retain…

--

--