机器学习笔记 - 模式识别的应用场景之一简单车牌识别
Posted 坐望云起
tags:
篇首语：本文由小常识网(cha138.com)小编为大家整理，主要介绍了机器学习笔记 - 模式识别的应用场景之一简单车牌识别相关的知识，希望对你有一定的参考价值。
一、关于模式识别
模式（Pattern）是指具有某种特定性质的感知对象。一般情况下，待观察的事物都具有时空分布信息。模式识别（Pattern Recognition）又称为模式分类，指对待观察事物的各种信息进行处理、描述、分类和解释的过程。按照有无训练样本，模式识别可分为监督模式识别和非监督模式识别两种。
模式识别的研究方向主要有两个：第一个是研究生物体是如何感知世界的；第二个是研究如何用机器（包括计算机）识别特定对象的模式。这些特定对象可以是字符、语音、图像等具体的事物，也可以是状态、程度、范围等抽象的表达。模式识别与数学、医学、心理学、语言学、物理学及计算机科学等都有关系。
https://skydance.blog.csdn.net/article/details/126520391下面的代码都来自别人的github，是基于图像处理+支持向量机实现的，也是模式识别的范畴。比较典型也易于理解，是一个用于了解模式识别比较好的入门示例。
二、车辆识别
对于传入的车牌图像，基于旋转校正、阈值分割、边缘检测等常用的图像分割算法。颜色分割算法/边缘检测算法完成车牌区域定位；然后对车牌区域校正，分割字符区域；最后导入预训练的SVM分类器，识别字符区域，输出识别结果。
1、定位车牌
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:
pic_rate = MAX_WIDTH / pic_width
img = cv2.resize(img, (MAX_WIDTH, int(pic_hight*pic_rate)), interpolation=cv2.INTER_LANCZOS4)
if resize_rate != 1:
img = cv2.resize(img, (int(pic_width*resize_rate), int(pic_hight*resize_rate)), interpolation=cv2.INTER_LANCZOS4)
pic_hight, pic_width = img.shape[:2]
print("h,w:", pic_hight, pic_width)
blur = 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.morphologyEx(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"], 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
try:
contours, hierarchy = cv2.findContours(img_edge2, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
except ValueError:
image, contours, hierarchy = cv2.findContours(img_edge2, cv2.RETR_TREE, cv2.CHAIN_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 = rect[1]
if area_width < area_height:
area_width, area_height = 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 = np.int0(box)
#oldimg = cv2.drawContours(oldimg, [box], 0, (0, 0, 255), 2)
#cv2.imshow("edge4", oldimg)
#cv2.waitKey(0)
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 rect[2] > -1 and rect[2] < 1:#创造角度，使得左、高、右、低拿到正确的值
angle = 1
else:
angle = rect[2]
rect = (rect[0], (rect[1][0]+5, rect[1][1]+5), angle)#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_point[0] > point[0]:
left_point = point
if low_point[1] > point[1]:
low_point = point
if heigth_point[1] < point[1]:
heigth_point = point
if right_point[0] < point[0]:
right_point = point
if left_point[1] <= right_point[1]:#正角度
new_right_point = [right_point[0], heigth_point[1]]
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.warpAffine(oldimg, M, (pic_width, pic_hight))
point_limit(new_right_point)
point_limit(heigth_point)
point_limit(left_point)
card_img = dst[int(left_point[1]):int(heigth_point[1]), int(left_point[0]):int(new_right_point[0])]
card_imgs.append(card_img)
#cv2.imshow("card", card_img)
#cv2.waitKey(0)
elif left_point[1] > right_point[1]:#负角度
new_left_point = [left_point[0], heigth_point[1]]
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, pic_hight))
point_limit(right_point)
point_limit(heigth_point)
point_limit(new_left_point)
card_img = dst[int(right_point[1]):int(heigth_point[1]), int(new_left_point[0]):int(right_point[0])]
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
colors = []
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 range(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
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(color)
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 = False
if yl >= yh:
yl = 0
yh = row_num
need_accurate = True
if xl >= xr:
xl = 0
xr = col_num
need_accurate = True
card_imgs[card_index] = card_img[yl: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，需要再试一次
card_img = card_imgs[card_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_imgs[card_index] = card_img[yl: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2、识别字符
车牌字符识别使用的算法是opencv的SVM， opencv的SVM使用代码来自于opencv附带的sample，StatModel类和SVM类都是sample中的代码。SVM训练使用的训练样本来自于github上的EasyPR的c++版本。由于训练样本有限，你测试时会发现，车牌字符识别，可能存在误差，尤其是第一个中文字符出现的误差概率较大。源码中有EasyPR中的训练样本，在train目录下，如果要重新训练请解压在当前目录下，并删除原始训练数据文件svm.dat和svmchinese.dat。
#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 ("blue", "yello", "green"):
card_img = card_imgs[i]
gray_img = cv2.cvtColor(card_img, cv2.COLOR_BGR2GRAY)
#黄、绿车牌字符比背景暗、与蓝车牌刚好相反，所以黄、绿车牌需要反向
if color == "green" or color == "yello":
gray_img = cv2.bitwise_not(gray_img)
ret, gray_img = cv2.threshold(gray_img, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)
#查找水平直方图波峰
x_histogram = np.sum(gray_img, axis=1)
x_min = np.min(x_histogram)
x_average = np.sum(x_histogram)/x_histogram.shape[0]
x_threshold = (x_min + x_average)/2
wave_peaks = find_waves(x_threshold, x_histogram)
if len(wave_peaks) == 0:
print("peak less 0:")
continue
#认为水平方向，最大的波峰为车牌区域
wave = max(wave_peaks, key=lambda x:x[1]-x[0])
gray_img = gray_img[wave[0]:wave[1]]
#查找垂直直方图波峰
row_num, col_num= gray_img.shape[:2]
#去掉车牌上下边缘1个像素，避免白边影响阈值判断
gray_img = gray_img[1:row_num-1]
y_histogram = np.sum(gray_img, axis=0)
y_min = np.min(y_histogram)
y_average = np.sum(y_histogram)/y_histogram.shape[0]
y_threshold = (y_min + y_average)/5#U和0要求阈值偏小，否则U和0会被分成两半
wave_peaks = find_waves(y_threshold, y_histogram)
#for wave in wave_peaks:
# cv2.line(card_img, pt1=(wave[0], 5), pt2=(wave[1], 5), color=(0, 0, 255), thickness=2)
#车牌字符数应大于6
if len(wave_peaks) <= 6:
print("peak less 1:", len(wave_peaks))
continue
wave = max(wave_peaks, key=lambda x:x[1]-x[0])
max_wave_dis = wave[1] - wave[0]
#判断是否是左侧车牌边缘
if wave_peaks[0][1] - wave_peaks[0][0] < max_wave_dis/3 and wave_peaks[0][0] == 0:
wave_peaks.pop(0)
#组合分离汉字
cur_dis = 0
for i,wave in enumerate(wave_peaks):
if wave[1] - wave[0] + cur_dis > max_wave_dis * 0.6:
break
else:
cur_dis += wave[1] - wave[0]
if i > 0:
wave = (wave_peaks[0][0], wave_peaks[i][1])
wave_peaks = wave_peaks[i+1:]
wave_peaks.insert(0, wave)
#去除车牌上的分隔点
point = wave_peaks[2]
if point[1] - point[0] < max_wave_dis/3:
point_img = gray_img[:,point[0]:point[1]]
if np.mean(point_img) < 255/5:
wave_peaks.pop(2)
if len(wave_peaks) <= 6:
print("peak less 2:", len(wave_peaks))
continue
part_cards = seperate_card(gray_img, wave_peaks)
for i, part_card in enumerate(part_cards):
#可能是固定车牌的铆钉
if np.mean(part_card) < 255/5:
print("a point")
continue
part_card_old = part_card
#w = abs(part_card.shape[1] - SZ)//2
w = part_card.shape[1] // 3
part_card = cv2.copyMakeBorder(part_card, 0, 0, w, w, cv2.BORDER_CONSTANT, value = [0,0,0])
part_card = cv2.resize(part_card, (SZ, SZ), interpolation=cv2.INTER_AREA)
#cv2.imshow("part", part_card_old)
#cv2.waitKey(0)
#cv2.imwrite("u.jpg", part_card)
#part_card = deskew(part_card)
part_card = preprocess_hog([part_card])
if i == 0:
resp = self.modelchinese.predict(part_card)
charactor = provinces[int(resp[0]) - PROVINCE_START]
else:
resp = self.model.predict(part_card)
charactor = chr(resp[0])
#判断最后一个数是否是车牌边缘，假设车牌边缘被认为是1
if charactor == "1" and i == len(part_cards)-1:
if part_card_old.shape[0]/part_card_old.shape[1] >= 8:#1太细，认为是边缘
print(part_card_old.shape)
continue
predict_result.append(charactor)
roi = card_img
card_color = color
break
return predict_result, roi, card_color#识别到的字符、定位的车牌图像、车牌颜色
识别结果如下
h,w: 394 631
len(contours) 3
2
精确定位
blue
3800 21 0 67 9 4641
no
1 420 897 24 270 20145
['粤', 'X', '8', '3', '3', '3', '8']车牌定位算法的参数受图像分辨率、色偏、车距影响，如果是基于深度学习的算法效果可能会更好。
以上是关于机器学习笔记 - 模式识别的应用场景之一简单车牌识别的主要内容，如果未能解决你的问题，请参考以下文章