车牌识别Python程序

1、# -*- coding: utf-8 -*-_author_ = 'd1bysj'import pymysqldb = pymysql.connect(host = '', # 远程主机的ip地址， user = '', # MySQL用户名 db = '', # database名 passwd = '', # 数据库密码 port = 3306, #数据库监听端口，默认3306 charset = "utf8") #指定utf8编码的连接cur= db.cursor()sql="

2、select * from sex"try: cur.execute(sql) re=cur.fetchall() for it in re: name = it0 num = it1 print(name,num)except Exception as e: raise efinally: db.close()import cv2import numpy as npfrom numpy.linalg import normimport sysimport osimport jsonSZ = 20 # 训练图片长宽MAX_WIDTH = 1000 # 原始图片最大宽度Min_Area

3、 = 2000 # 车牌区域允许最大面积PROVINCE_START = 1000# 读取图片文件def imreadex(filename): return cv2.imdecode(np.fromfile(filename, dtype=np.uint8), cv2.IMREAD_COLOR)def point_limit(point): if point0 < 0: point0 = 0 if point1 < 0: point1 = 0# 根据设定的阈值和图片直方图，找出波峰，用于分隔字符def find_waves(threshold, histogram): up_po

4、int = -1 # 上升点 is_peak = False if histogram0 > threshold: up_point = 0 is_peak = True wave_peaks = for i, x in enumerate(histogram): if is_peak and x < threshold: if i - up_point > 2: is_peak = False wave_peaks.append(up_point, i) elif not is_peak and x >= threshold: is_peak = True up_po

5、int = i if is_peak and up_point != -1 and i - up_point > 4: wave_peaks.append(up_point, i) return wave_peaks# 根据找出的波峰，分隔图片，从而得到逐个字符图片def seperate_card(img, waves): part_cards = for wave in waves: part_cards.append(img:, wave0:wave1) return part_cards# 来自opencv的sample，用于svm训练def deskew(img): m = c

6、v2.moments(img) if abs(m'mu02') < 1e-2: return img.copy() skew = m'mu11' / m'mu02' M = np.float32(1, skew, -0.5 * SZ * skew, 0, 1, 0) img = cv2.warpAffine(img, M, (SZ, SZ), flags=cv2.WARP_INVERSE_MAP | cv2.INTER_LINEAR) return img# 来自opencv的sample，用于svm训练def preprocess_hog

7、(digits): samples = for img in digits: gx = cv2.Sobel(img, cv2.CV_32F, 1, 0) gy = cv2.Sobel(img, cv2.CV_32F, 0, 1) mag, ang = cv2.cartToPolar(gx, gy) bin_n = 16 bin = 32(bin_n * ang / (2 * np.pi) bin_cells = bin:10, :10, bin10:, :10, bin:10, 10:, bin10:, 10: mag_cells = mag:10, :10, mag10:, :1

8、0, mag:10, 10:, mag10:, 10: hists = np.bincount(b.ravel(), m.ravel(), bin_n) for b, m in zip(bin_cells, mag_cells) hist = np.hstack(hists) # transform to Hellinger kernel eps = 1e-7 hist /= hist.sum() + eps hist = np.sqrt(hist) hist /= norm(hist) + eps samples.append(hist) return np.float32(samples)

9、# 不能保证包括所有省份provinces = "zh_cuan", "川", "zh_e", "鄂", "zh_gan", "赣", "zh_gan1", "甘", "zh_gui", "贵", "zh_gui1", "桂", "zh_hei", "黑", "zh_hu", "沪&quo

10、t;, "zh_ji", "冀", "zh_jin", "津", "zh_jing", "京", "zh_jl", "吉", "zh_liao", "辽", "zh_lu", "鲁", "zh_meng", "蒙", "zh_min", "闽", "zh_ning&qu

11、ot;, "宁", "zh_qing", "靑", "zh_qiong", "琼", "zh_shan", "陕", "zh_su", "苏", "zh_sx", "晋", "zh_wan", "皖", "zh_xiang", "湘", "zh_xin", "新&quo

12、t;, "zh_yu", "豫", "zh_yu1", "渝", "zh_yue", "粤", "zh_yun", "云", "zh_zang", "藏", "zh_zhe", "浙"class StatModel(object): def load(self, fn): self.model = self.model.load(fn) def save(s

13、elf, fn): self.model.save(fn)class SVM(StatModel): def _init_(self, C=1, gamma=0.5): self.model = cv2.ml.SVM_create() self.model.setGamma(gamma) self.model.setC(C) self.model.setKernel(cv2.ml.SVM_RBF) self.model.setType(cv2.ml.SVM_C_SVC) # 训练svm def train(self, samples, responses): self.model.train(

14、samples, cv2.ml.ROW_SAMPLE, responses) # 字符识别 def predict(self, samples): r = self.model.predict(samples) return r1.ravel()class CardPredictor: def _init_(self): # 车牌识别的部分参数保存在js中，便于根据图片分辨率做调整 f = open('config.js') j = json.load(f) for c in j"config": print(c) if c"open":

15、 self.cfg = c.copy() break else: raise RuntimeError('没有设置有效配置参数') def _del_(self): self.save_traindata() def train_svm(self): # 识别英文字母和数字 self.model = SVM(C=1, gamma=0.5) # 识别中文 self.modelchinese = SVM(C=1, gamma=0.5) if os.path.exists("svm.dat"): self.model.load("svm.dat"

16、;) else: chars_train = chars_label = for root, dirs, files in os.walk("trainchars2"): if len(os.path.basename(root) > 1: continue root_int = ord(os.path.basename(root) for filename in files: filepath = os.path.join(root, filename) digit_img = cv2.imread(filepath) digit_img = cv2.cvtColo

17、r(digit_img, cv2.COLOR_BGR2GRAY) chars_train.append(digit_img) # chars_label.append(1) chars_label.append(root_int) chars_train = list(map(deskew, chars_train) chars_train = preprocess_hog(chars_train) # chars_train = chars_train.reshape(-1, 20, 20).astype(np.float32) chars_label = np.array(chars_la

18、bel) print(chars_train.shape) self.model.train(chars_train, chars_label) if os.path.exists("svmchinese.dat"): self.modelchinese.load("svmchinese.dat") else: chars_train = chars_label = for root, dirs, files in os.walk("traincharsChinese"): if not os.path.basename(root).

19、startswith("zh_"): continue pinyin = os.path.basename(root) index = provinces.index(pinyin) + PROVINCE_START + 1 # 1是拼音对应的汉字 for filename in files: filepath = os.path.join(root, filename) digit_img = cv2.imread(filepath) digit_img = cv2.cvtColor(digit_img, cv2.COLOR_BGR2GRAY) chars_train.a

20、ppend(digit_img) # chars_label.append(1) chars_label.append(index) chars_train = list(map(deskew, chars_train) chars_train = preprocess_hog(chars_train) # chars_train = chars_train.reshape(-1, 20, 20).astype(np.float32) chars_label = np.array(chars_label) print(chars_train.shape) self.modelchinese.t

21、rain(chars_train, chars_label) def save_traindata(self): if not os.path.exists("svm.dat"): self.model.save("svm.dat") if not os.path.exists("svmchinese.dat"): self.modelchinese.save("svmchinese.dat") def accurate_place(self, card_img_hsv, limit1, limit2, color

22、): row_num, col_num = card_img_hsv.shape:2 xl = col_num xr = 0 yh = 0 yl = row_num # col_num_limit = self.cfg"col_num_limit" row_num_limit = self.cfg"row_num_limit" col_num_limit = col_num * 0.8 if color != "green" else col_num * 0.5 # 绿色有渐变 for i in range(row_num): cou

23、nt = 0 for j in range(col_num): H = card_img_hsv.item(i, j, 0) S = card_img_hsv.item(i, j, 1) V = card_img_hsv.item(i, j, 2) if limit1 < H <= limit2 and 34 < S and 46 < V: count += 1 if count > col_num_limit: if yl > i: yl = i if yh < i: yh = i for j in range(col_num): count = 0

24、 for i in range(row_num): H = card_img_hsv.item(i, j, 0) S = card_img_hsv.item(i, j, 1) V = card_img_hsv.item(i, j, 2) if limit1 < H <= limit2 and 34 < S and 46 < V: count += 1 if count > row_num - row_num_limit: if xl > j: xl = j if xr < j: xr = j return xl, xr, yh, yl def pred

25、ict(self, car_pic): if type(car_pic) = type(""): img = imreadex(car_pic) else: img = car_pic pic_hight, pic_width = img.shape:2 if pic_width > MAX_WIDTH: resize_rate = MAX_WIDTH / pic_width img = cv2.resize(img, (MAX_WIDTH, int(pic_hight * resize_rate), interpolation=cv2.INTER_AREA) blu

26、r = self.cfg"blur" # 高斯去噪 if blur > 0: img = cv2.GaussianBlur(img, (blur, blur), 0) # 图片分辨率调整 oldimg = img img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) # equ = cv2.equalizeHist(img) # img = np.hstack(img, equ) # 去掉图像中不会是车牌的区域 kernel = np.ones(20, 20), np.uint8) img_opening = cv2.morpholo

27、gyEx(img, cv2.MORPH_OPEN, kernel) img_opening = cv2.addWeighted(img, 1, img_opening, -1, 0); # 找到图像边缘 ret, img_thresh = cv2.threshold(img_opening, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU) img_edge = cv2.Canny(img_thresh, 100, 200) # 使用开运算和闭运算让图像边缘成为一个整体 kernel = np.ones(self.cfg"morphologyr

28、", self.cfg"morphologyc"), np.uint8) img_edge1 = cv2.morphologyEx(img_edge, cv2.MORPH_CLOSE, kernel) img_edge2 = cv2.morphologyEx(img_edge1, cv2.MORPH_OPEN, kernel) # 查找图像边缘整体形成的矩形区域，可能有很多，车牌就在其中一个矩形区域中 image, contours, hierarchy = cv2.findContours(img_edge2, cv2.RETR_TREE, cv2.CHAIN_

29、APPROX_SIMPLE) contours = cnt for cnt in contours if cv2.contourArea(cnt) > Min_Area print('len(contours)', len(contours) # 一一排除不是车牌的矩形区域 car_contours = for cnt in contours: rect = cv2.minAreaRect(cnt) area_width, area_height = rect1 if area_width < area_height: area_width, area_height

30、 = area_height, area_width wh_ratio = area_width / area_height # print(wh_ratio) # 要求矩形区域长宽比在2到5.5之间，2到5.5是车牌的长宽比，其余的矩形排除 if wh_ratio > 2 and wh_ratio < 5.5: car_contours.append(rect) box = cv2.boxPoints(rect) box = 0(box) # oldimg = cv2.drawContours(oldimg, box, 0, (0, 0, 255), 2) # cv2

31、.imshow("edge4", oldimg) # print(rect) print(len(car_contours) print("精确定位") card_imgs = # 矩形区域可能是倾斜的矩形，需要矫正，以便使用颜色定位 for rect in car_contours: if rect2 > -1 and rect2 < 1: # 创造角度，使得左、高、右、低拿到正确的值 angle = 1 else: angle = rect2 rect = (rect0, (rect10 + 5, rect11 + 5), angle)

32、# 扩大范围，避免车牌边缘被排除 box = cv2.boxPoints(rect) heigth_point = right_point = 0, 0 left_point = low_point = pic_width, pic_hight for point in box: if left_point0 > point0: left_point = point if low_point1 > point1: low_point = point if heigth_point1 < point1: heigth_point = point if right_point0

33、< point0: right_point = point if left_point1 <= right_point1: # 正角度 new_right_point = right_point0, heigth_point1 pts2 = np.float32(left_point, heigth_point, new_right_point) # 字符只是高度需要改变 pts1 = np.float32(left_point, heigth_point, right_point) M = cv2.getAffineTransform(pts1, pts2) dst = cv2.

34、warpAffine(oldimg, M, (pic_width, pic_hight) point_limit(new_right_point) point_limit(heigth_point) point_limit(left_point) card_img = dstint(left_point1):int(heigth_point1), int(left_point0):int(new_right_point0) card_imgs.append(card_img) # cv2.imshow("card", card_img) # cv2.waitKey(0) e

35、lif left_point1 > right_point1: # 负角度 new_left_point = left_point0, heigth_point1 pts2 = np.float32(new_left_point, heigth_point, right_point) # 字符只是高度需要改变 pts1 = np.float32(left_point, heigth_point, right_point) M = cv2.getAffineTransform(pts1, pts2) dst = cv2.warpAffine(oldimg, M, (pic_width, p

36、ic_hight) point_limit(right_point) point_limit(heigth_point) point_limit(new_left_point) card_img = dstint(right_point1):int(heigth_point1), int(new_left_point0):int(right_point0) card_imgs.append(card_img) # cv2.imshow("card", card_img) # cv2.waitKey(0) # 开始使用颜色定位，排除不是车牌的矩形，目前只识别蓝、绿、黄车牌 c

37、olors = for card_index, card_img in enumerate(card_imgs): green = yello = blue = black = white = 0 card_img_hsv = cv2.cvtColor(card_img, cv2.COLOR_BGR2HSV) # 有转换失败的可能，原因来自于上面矫正矩形出错 if card_img_hsv is None: continue row_num, col_num = card_img_hsv.shape:2 card_img_count = row_num * col_num for i in r

38、ange(row_num): for j in range(col_num): H = card_img_hsv.item(i, j, 0) S = card_img_hsv.item(i, j, 1) V = card_img_hsv.item(i, j, 2) if 11 < H <= 34 and S > 34: # 图片分辨率调整 yello += 1 elif 35 < H <= 99 and S > 34: # 图片分辨率调整 green += 1 elif 99 < H <= 124 and S > 34: # 图片分辨率调整

39、 blue += 1 if 0 < H < 180 and 0 < S < 255 and 0 < V < 46: black += 1 elif 0 < H < 180 and 0 < S < 43 and 221 < V < 225: white += 1 color = "no" limit1 = limit2 = 0 if yello * 2 >= card_img_count: color = "yello" limit1 = 11 limit2 = 34 # 有的图

40、片有色偏偏绿 elif green * 2 >= card_img_count: color = "green" limit1 = 35 limit2 = 99 elif blue * 2 >= card_img_count: color = "blue" limit1 = 100 limit2 = 124 # 有的图片有色偏偏紫 elif black + white >= card_img_count * 0.7: # TODO color = "bw" print(color) colors.append(col

41、or) print(blue, green, yello, black, white, card_img_count) # cv2.imshow("color", card_img) # cv2.waitKey(0) if limit1 = 0: continue # 以上为确定车牌颜色 # 以下为根据车牌颜色再定位，缩小边缘非车牌边界 xl, xr, yh, yl = self.accurate_place(card_img_hsv, limit1, limit2, color) if yl = yh and xl = xr: continue need_accurate

42、 = False if yl >= yh: yl = 0 yh = row_num need_accurate = True if xl >= xr: xl = 0 xr = col_num need_accurate = True card_imgscard_index = card_imgyl:yh, xl:xr if color != "green" or yl < (yh - yl) / 4 else card_img yl - ( yh - yl) / 4:yh, xl:xr if need_accurate: # 可能x或y方向未缩小，需要再试

43、一次 card_img = card_imgscard_index card_img_hsv = cv2.cvtColor(card_img, cv2.COLOR_BGR2HSV) xl, xr, yh, yl = self.accurate_place(card_img_hsv, limit1, limit2, color) if yl = yh and xl = xr: continue if yl >= yh: yl = 0 yh = row_num if xl >= xr: xl = 0 xr = col_num card_imgscard_index = card_imgyl:yh, xl:xr if color != "green" or yl < (yh - yl) / 4 else card_img yl - ( yh - yl) / 4:yh, xl:xr # 以上为车牌定位 # 以下为识别车牌中的字符 predict_result = roi = None card_color = None for i, color in enumerate(colors): if color in ("bl