Python实现校园卡目标检测与文字识别系统

 1pwd?=?os.getcwd()
 2logger.info('Current?path?is:{}'.format(pwd))
 3#?提取正样本
 4pos_dir?=?os.path.join(pwd,?'Positive')
 5if?os.path.exists(pos_dir):
 6????logger.info('Positive?data?path?is:{}'.format(pos_dir))
 7????pos?=?os.listdir(pos_dir)
 8????logger.info('Positive?samples?number:{}'.format(len(pos)))
 9#?提取负样本
10neg_dir?=?os.path.join(pwd,?'Negative')
11if?os.path.exists(neg_dir):
12????logger.info('Negative?data?path?is:{}'.format(neg_dir))
13????neg?=?os.listdir(neg_dir)
14????logger.info('Negative?samples?number:{}'.format(len(neg)))
15#?提取测试集
16test_dir?=?os.path.join(pwd,?'TestData')
17if?os.path.exists(test_dir):
18????logger.info('Test?data?path?is:{}'.format(test_dir))
19????test?=?os.listdir(test_dir)
20????logger.info('Test?samples?number:{}'.format(len(test)))

 1pwd?=?os.getcwd()
 2pos_dir?=?os.path.join(pwd,?'Positive')
 3neg_dir?=?os.path.join(pwd,?'Negative')
 4samples?=?[]
 5labels?=?[]
 6for?f?in?pos:
 7????file_path?=?os.path.join(pos_dir,?f)
 8????if?os.path.exists(file_path):
 9????????samples.append(file_path)
10????????labels.append(1.)
11for?f?in?neg:
12????file_path?=?os.path.join(neg_dir,?f)
13????if?os.path.exists(file_path):
14????????samples.append(file_path)
15????????labels.append(-1.)
16#?labels?要转换成numpy数组，类型为np.int32
17labels?=?np.int32(labels)
18labels_len?=?len(pos)?+?len(neg)
19labels?=?np.resize(labels,?(labels_len,?1))

 1train?=?[]
 2logger.info('Extracting?HOG?Descriptors...')
 3num?=?0.
 4total?=?len(samples)
 5for?f?in?samples:
 6????num?+=?1.
 7????logger.info('Processing?{}?{:2.1f}%'.format(f,?num/total*100))
 8????hog?=?cv2.HOGDescriptor((64,128),?(16,16),?(8,8),?(8,8),?9)
 9????#?hog?=?cv2.HOGDescriptor()
10????img?=?cv2.imread(f,?-1)
11????img?=?cv2.resize(img,?(64,128))
12????descriptors?=?hog.compute(img)
13????logger.info('hog?feature?descriptor?size:?{}'.format(descriptors.shape))????#?(3780,?1)
14????train.append(descriptors)
15train?=?np.float32(train)
16train?=?np.resize(train,?(total,?3780))

 1logger.info('Configuring?SVM?classifier.')
 2svm?=?cv2.ml.SVM_create()
 3svm.setCoef0(0.0)
 4svm.setDegree(3)
 5criteria?=?(cv2.TERM_CRITERIA_MAX_ITER?+?cv2.TERM_CRITERIA_EPS,?1000,?1e-3)
 6svm.setTermCriteria(criteria)
 7svm.setGamma(0)
 8svm.setKernel(cv2.ml.SVM_LINEAR)
 9svm.setNu(0.5)
10svm.setP(0.1)??#?for?EPSILON_SVR,?epsilon?in?loss?function?
11svm.setC(0.01)??#?From?paper,?soft?classifier
12svm.setType(cv2.ml.SVM_EPS_SVR)
13logger.info('Starting?training?svm.')
14svm.train(train,?cv2.ml.ROW_SAMPLE,?labels)
15logger.info('Training?done.')
16pwd?=?os.getcwd()
17model_path?=?os.path.join(pwd,?'svm.xml')
18svm.save(model_path)
19logger.info('Trained?SVM?classifier?is?saved?as:?{}'.format(model_path))
20

 1hog?=?cv2.HOGDescriptor()
 2hog.setSVMDetector(cv2.HOGDescriptor_getDefaultPeopleDetector())
 3pwd?=?os.getcwd()
 4test_dir?=?os.path.join(pwd,?'TestData')
 5cap=cv2.VideoCapture("http://admin:admin@192.168.137.124:8081/")
 6while?True:
 7????_,?frame?=?cap.read()
 8????rects,?_?=?hog.detectMultiScale(frame,?winStride=(4,?4),?padding=(8,?8),?scale=1.05)
 9????for?(x,?y,?w,?h)?in?rects:
10????????cv2.rectangle(frame,?(x,?y),?(x?+?w,?y?+?h),?(0,?0,?255),?2)
11????cv2.imshow('Detect',?frame)
12????c?=?cv2.waitKey(1)?&?0xff
13????if?c?==?27:
14????????break

1img=cv2.imread("TestData/0.jpg")
2img=cv2.resize(img,(400,300))

1rectKernel=cv2.getStructuringElement(cv2.MORPH_RECT,(12,12))
2sqKernel=cv2.getStructuringElement(cv2.MORPH_RECT,(5,5))

1gray=cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
2#执行Top-hat形态操作，将结果存储为?tophat,Top-hat操作显示了深色背景下的亮区
3tophat=cv2.morphologyEx(gray,cv2.MORPH_TOPHAT,rectKernel)

1gradx=cv2.Sobel(tophat,ddepth=cv2.CV_32F,dx=1,dy=0,ksize=-1)
2gradx=np.absolute(gradx)
3(minval,maxval)=(np.min(gradx),np.max(gradx))
4gradx=(255*((gradx-minval)/(maxval-minval)))
5gradx=gradx.astype("uint8")
6#执行gradX?图像的Otsu和二进制阈值，然后是另一个关闭操作,对数字分段
7gradx=cv2.morphologyEx(gradx,cv2.MORPH_CLOSE,rectKernel)

1thresh=cv2.threshold(gradx,0,255,cv2.THRESH_BINARY|cv2.THRESH_OTSU)[1]

1kernel=np.ones((7,7),np.uint8)
2dilate=cv2.dilate(thresh,kernel,iterations=1)

 1#找到轮廓并初始化数字分组位置列表
 2cnts=cv2.findContours(thresh,cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_SIMPLE)
 3cnts=imutils.grab_contours(cnts)
 4locs?=?[]
 5#循环遍历轮廓，同时根据每个的宽高比进行过滤，允许我们从信用卡的其他不相关区域修剪数字组位置
 6for?(i,?c)?in?enumerate(cnts):
 7????(x,?y,?w,?h)?=?cv2.boundingRect(c)
 8????#我们需要提取的区域长宽比是大于1，去除杂项
 9????ar?=?w/h
10????if?ar?>?1:
11????????locs.append((x,?y,?w,?h))
12#从左到右对分组进行排序，并初始化信用卡数字列表
13locs?=?sorted(locs,?key=lambda?x:x[0])
14print(locs)
15for?i?in?locs:
16????print(i)
17????image=gray[i[1]:i[1]+i[3],i[0]:i[0]+i[2]]
18????cv2.imwrite("temp.jpg",image)
19????APP_ID?=?'23109663'??#?刚才获取的?ID，下同
20????API_KEY?=?'4rWRc7ensuq0Bf8NGs8cGuaz'
21????SECRECT_KEY?=?'bWWS8ugAs2wGGx78yTUiMccpQpWt0UlY'
22????client?=?AipOcr(APP_ID,?API_KEY,?SECRECT_KEY)
23????tt?=?open("temp.jpg",?'rb')
24????img?=?tt.read()
25????message?=?client.basicGeneral(img)??#通用文字识别
26????print(message)
27????cv2.imshow(str(i)+"2",image)
28????cv2.waitKey(1)
29cv2.waitKey(0)