opencv python訓練人臉識別

總計分為三個步驟

　　一、捕獲人臉照片

　　二、對捕獲的照片進行訓練

　　三、加載訓練的數據，識別

 

使用python3.6.8，opencv，numpy，pil

第一步：通過筆記本前置攝像頭捕獲臉部圖片

　　將捕獲的照片存在picData文件夾中，並格式為user.id.num.jpg。id在識別時和人名數組一一對應。

import numpy as np
import cv2

cap = cv2.VideoCapture(0)
face_cascade = cv2.CascadeClassifier("data/haarcascade_frontalface_default.xml")
sampleNum = 0
Id = input('請輸入id：')

while True:
    ret, img = cap.read()
    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
    faces = face_cascade.detectMultiScale(gray, 1.3, 5)
    for (x, y, w, h) in faces:
        img = cv2.rectangle(img, (x, y), (x + w, y + h), (255, 0, 0), 2)
        # 增加例子數
        sampleNum = sampleNum + 1
       
        # 把照片保存到數據集文件夾
        cv2.imwrite(
            "picData/user." + str(Id) + "." + str(sampleNum) + ".jpg",
            gray[y : y + h, x : x + w],
        )
    cv2.imshow("img", img)
    if cv2.waitKey(1) & 0xFF == ord("q"):
        break
    if sampleNum == 3000:
        break

cap.release()
cv2.destroyAllWindows()

 

第二步：訓練數據

　　將訓練好的數據存儲在data/trainner.yml中

import cv2
import os
import numpy as np
from PIL import Image

recognizer = cv2.face.LBPHFaceRecognizer_create()
detector = cv2.CascadeClassifier("data/haarcascade_frontalface_default.xml")


def get_images_and_labels(path):
    image_paths = [os.path.join(path, f) for f in os.listdir(path)]
    face_samples = []
    ids = []

    for image_path in image_paths:
        image = Image.open(image_path).convert("L")
        image_np = np.array(image, "uint8")
        if os.path.split(image_path)[-1].split(".")[-1] != "jpg":
            continue
        image_id = int(os.path.split(image_path)[-1].split(".")[1])
        faces = detector.detectMultiScale(image_np)
        for (x, y, w, h) in faces:
            face_samples.append(image_np[y : y + h, x : x + w])
            ids.append(image_id)

    return face_samples, ids


faces, Ids = get_images_and_labels("picData")
recognizer.train(faces, np.array(Ids))
recognizer.save("data/trainner.yml")

第三步：人臉識別

 　　加載第二步訓練的數據，定義需要識別的人名。

import cv2

recognizer = cv2.face.LBPHFaceRecognizer_create()
recognizer.read('data/trainner.yml')
faceCascade = cv2.CascadeClassifier("data/haarcascade_frontalface_default.xml")
font = cv2.FONT_HERSHEY_SIMPLEX

idnum = 0

names = ['kAng']

cam = cv2.VideoCapture(0)
minW = 0.1*cam.get(3)
minH = 0.1*cam.get(4)

while True:
    ret, img = cam.read()
    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

    faces = faceCascade.detectMultiScale(
        gray,
        scaleFactor=1.2,
        minNeighbors=5,
        minSize=(int(minW), int(minH))
    )

    for (x, y, w, h) in faces:
        cv2.rectangle(img, (x, y), (x+w, y+h), (0, 255, 0), 2)
        idnum, confidence = recognizer.predict(gray[y:y+h, x:x+w])

        if confidence >50:
            idnum = names[idnum]
            confidence = "{0}%".format(round(confidence))
        else:
            idnum = "unknown"
            confidence = "{0}%".format(round(confidence))

        cv2.putText(img, str(idnum), (x+5, y-5), font, 1, (0, 0, 255), 1)
        cv2.putText(img, str(confidence), (x+5, y+h-5), font, 1, (255, 255, 0), 1)

    cv2.imshow('camera', img)
    k = cv2.waitKey(10)
    if k == 27:
        break

cam.release()
cv2.destroyAllWindows()

　　

　效果圖：

 

 

 

參考：https://segmentfault.com/a/1190000014943784（詳細解析）