Python OpenCV机器学习之图像识别详解

目录

• 背景
• 一、人脸识别
• 二、车牌识别
• 三、DNN图像分类

# 创建Haar级联器
facer = cv2.CascadeClassifier("./haarcascades/haarcascade_frontalface_default.xml")
# 导入人脸图片并灰度化
img = cv2.imread("p3.png")
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# 调用接口
faces = facer.detectMultiScale(gray, 1.1, 5)

for (x,y,w,h) in faces:
    cv2.rectangle(img, (x,y), (x+w, y+h), (0,0,255), 2)

cv2.imshow("img", img)
cv2.waitKey()

# 创建Haar级联器
facer = cv2.CascadeClassifier("./haarcascades/haarcascade_frontalface_default.xml")
eyer = cv2.CascadeClassifier("./haarcascades/haarcascade_eye.xml")
# 导入人脸图片并灰度化
img = cv2.imread("p3.png")
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# 调用接口
faces = facer.detectMultiScale(gray, 1.1, 5)
i = 0
for (x,y,w,h) in faces:
    cv2.rectangle(img, (x,y), (x+w, y+h), (0,0,255), 2)
    ROI_img = img[y:y+h, x:x+w]
    eyes = eyer.detectMultiScale(ROI_img, 1.1, 5)
    for (x,y,w,h) in eyes:
        cv2.rectangle(ROI_img, (x,y), (x+w, y+h), (0,255,0), 2)
    i += 1
    name = "img"+str(i)
    cv2.imshow(name, ROI_img)
cv2.waitKey()

import pytesseract
# 创建Haar级联器
carer = cv2.CascadeClassifier("./haarcascades/haarcascade_russian_plate_number.xml")
# 导入人脸图片并灰度化
img = cv2.imread("chinacar.jpeg")
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# 调用接口 
cars = carer.detectMultiScale(gray, 1.1, 3)
for (x,y,w,h) in cars:
    cv2.rectangle(img, (x,y), (x+w, y+h), (0,0,255), 2)
# 提取ROI
roi = gray[y:y+h, x:x+w]
# 二值化
ret, roi_bin = cv2.threshold(roi, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)
# 文字识别
pytesseract.pytesseract.tesseract_cmd = r"D:Tesseract_OCR	esseract.exe"
text = pytesseract.image_to_string(roi, lang="chi_sim+eng",cOnfig="--psm 8 --oem 3")
print(text)
cv2.putText(img, text, (20,100), cv2.FONT_HERSHEY_SIMPLEX, 2, (0,0,255), 3)
cv2.imshow("img", img)
cv2.waitKey()

# 导入模型
cOnfig= "./model/bvlc_googlenet.prototxt"
model = "./model/bvlc_googlenet.caffemodel"
net = dnn.readNetFromCaffe(config, model)

# 加载图片，转成张量
img = cv2.imread("./smallcat.jpeg")
blob = dnn.blobFromImage(img, 1.0, (224,224), (104,117,123))

# 模型推理
net.setInput(blob)
r = net.forward()
idxs = np.argsort(r[0])[::-1][:5]

# 分类结果展示
path = "./model/synset_words.txt"
with open(path, "rt") as f:
    classes = [x[x.find(" ")+1:]for x in f]
for (i, idx) in enumerate(idxs):
# 将结果展示在图像上
    if i == 0:
        text = "Label: {}, {:.2f}%".format(classes[idx],
            r[0][idx] * 100)
        cv2.putText(img, text, (5, 25),  cv2.FONT_HERSHEY_SIMPLEX,
            0.7, (0, 0, 255), 2)
# 显示图像
cv2.imshow("Image", img)
cv2.waitKey(0)