opencv+python识别鼻孔并打印鼻孔中心坐标

python+opencv识别鼻孔并打印鼻孔中心坐标

代码

import cv2
import imutils
# 人脸识别分类器
faceCascade = cv2.CascadeClassifier(
    r"D:\PYcharm\PyCharm Community Edition 2020.3.3\venv\Lib\site-packages\cv2\data\haarcascade_frontalface_default.xml")
# 识别眼睛的分类器
# eyeCascade = cv2.CascadeClassifier(r'D:\PYcharm\PyCharm Community Edition 2020.3.3\venv\Lib\site-packages\cv2\data\haarcascade_eye.xml')
eyeCascade = cv2.CascadeClassifier(
    r'D:\MATLAB\mcr\toolbox\vision\visionutilities\classifierdata\cascade\haar\haarcascade_mcs_nose.xml')
# 开启摄像头
cap = cv2.VideoCapture(0)
ok = True
nosej=["左鼻孔","右鼻孔"]
center=[";","\n"]
while ok:
    # 读取摄像头中的图像，ok为是否读取成功的判断参数
    ok, img = cap.read()
    img2 = img
    # 转换成灰度图像
    gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
    # 人脸检测
    faces = faceCascade.detectMultiScale(
        gray,
        scaleFactor=1.2,
        minNeighbors=15,
        minSize=(32, 32)
    )
    # 在检测人脸的基础上检测眼睛
    for (x, y, w, h) in faces:
        fac_gray = gray[y: (y + h), x: (x + w)]
        result = []
        eyes = eyeCascade.detectMultiScale(fac_gray, 1.3, 5, cv2.CASCADE_SCALE_IMAGE, (40, 40), (80, 80))
        for (ex, ey, ew, eh) in eyes:
            # print(eyes[0])
            result.append((x + ex, y + ey, ew, eh))
            # print("www",result)
    # 画矩形
    for (x, y, w, h) in faces:
        cv2.rectangle(img, (x, y), (x + w, y + h), (255, 0, 0), 2)
    try:
        for (ex, ey, ew, eh) in result:
            cv2.rectangle(img, (ex, ey), (ex + ew, ey + eh), (0, 255, 0), 2)  # 鼻子
            img_eye_l = cv2.resize(img2[result[0][1]:result[0][1] + result[0][3], result[0][0]:result[0][0] + result[0][2]], (300, 300))
            img_eye_l = img_eye_l[60:240, 10:290]
            image = img_eye_l
            image = cv2.resize(image, (image.shape[1], image.shape[0]))
            gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)  # 灰度
            blurred = cv2.GaussianBlur(gray, (5, 5), 0)  # 5x5的内核的高斯平滑
            ##################################
            thresh = cv2.threshold(blurred, 40, 255, cv2.THRESH_BINARY_INV)[1]  # 阈值化，阈值化后形状被表示成黑色背景上的白色前景。
            #############################    ↑  (1,74)
            cv2.imshow("Image", thresh)
            # 在阈值图像中查找轮廓
            # 找到白色对应的边界点的集合
            cnts = cv2.findContours(thresh.copy(), cv2.RETR_EXTERNAL,
                                    cv2.CHAIN_APPROX_SIMPLE)
            cnts = imutils.grab_contours(cnts)
            # 计算轮廓中心
            m=1
            for c in cnts:
                m+=1
                n=m%2
                M = cv2.moments(c)
                cX = int(M["m10"] / M["m00"])
                cY = int(M["m01"] / M["m00"])
                # 在图像上绘制形状的轮廓和中心
                cv2.drawContours(image, [c], -1, (0, 255, 0), 2)
                cv2.circle(image, (cX, cY), 7, (255, 255, 255), -1)
                cv2.putText(image, "center", (cX - 20, cY - 20),
                            cv2.FONT_HERSHEY_SIMPLEX, 0.5, (255, 255, 255), 2)

                # 展示图片
                cv2.imshow("Image", image)
                # with open(file_path, 'w') as w_obj:
                #     w_obj.write(str(cX) +' ' + str(cY)+ "\n")
                cv2.waitKey(1)
                # print("左鼻孔:", cX, "右鼻孔:", cY)
                print("相对于鼻子的坐标："f"{nosej[n]}:"f"({cX},{cY})",end=center[0])
                print("相对于脸的坐标："f"{nosej[n]}:"f"({cX+x},{cY+y})",end=center[0])
                print("相对于摄像头的坐标："f"{nosej[n]}:"f"({cX + ex},{cY + ey})", end=center[1])
    except:
        pass

    cv2.imshow('video', img)

    k = cv2.waitKey(1)
    if k == 27:
        break
cap.release()
cv2.destroyAllWindows()