基于python+OpenCV的车牌号码识别

车牌识别行业已具备一定的市场规模,在电子警察、公路卡口、停车场、商业管理、汽修服务等领域已取得了部分应用。一个典型的车辆牌照识别系统一般包括以下4个部分:车辆图像获取、车牌定位、车牌字符分割和车牌字符识别

1、车牌定位的主要工作是从获取的车辆图像中找到汽车牌照所在位置,并把车牌从该区域中准确地分割出来
这里所采用的是利用车牌的颜色(黄色、蓝色、绿色) 来进行定位
#定位车牌 def color_position(img,output_path): colors = [([26,43,46], [34,255,255])
, # 黄色 ([100,43,46], [124,255,255]), # 蓝色 ([35, 43, 46], [77, 255, 255]) # 绿色 ]
hsv= cv2.cvtColor(img, cv2.COLOR_BGR2HSV) for (lower, upper) in colors: lower =
np.array(lower, dtype="uint8") # 颜色下限 upper = np.array(upper, dtype="uint8") #
颜色上限 # 根据阈值找到对应的颜色 mask= cv2.inRange(hsv, lowerb=lower, upperb=upper) output =
cv2.bitwise_and(img, img, mask=mask) k = mark_zone_color(output,output_path) if
k==1: return 1 # 展示图片 #cv2.imshow("image", img) #cv2.imshow("image-color",
output) #cv2.waitKey(0) return 0

2、将车牌提取出来
def mark_zone_color(src_img,output_img): #根据颜色在原始图像上标记 #转灰度 gray = cv2.cvtColor
(src_img,cv2.COLOR_BGR2GRAY) #图像二值化 ret,binary = cv2.threshold(gray,0,255,cv2.
THRESH_BINARY) #轮廓检测 x,contours,hierarchy = cv2.findContours(binary,cv2.
RETR_TREE,cv2.CHAIN_APPROX_NONE) #drawing = img #cv2.drawContours(drawing,
contours, -1, (0, 0, 255), 3) # 填充轮廓颜色 #cv2.imshow('drawing', drawing) #cv2.
waitKey(0) #print(contours) temp_contours = [] # 存储合理的轮廓 car_plates=[] if len(
contours)>0: for contour in contours: if cv2.contourArea(contour) > Min_Area:
temp_contours.append(contour) car_plates = [] for temp_contour in temp_contours:
rect_tupple= cv2.minAreaRect(temp_contour) rect_width, rect_height =
rect_tupple[1] if rect_width < rect_height: rect_width, rect_height =
rect_height, rect_width aspect_ratio = rect_width / rect_height # 车牌正常情况下宽高比在2 -
5.5之间 if aspect_ratio > 2 and aspect_ratio < 5.5: car_plates.append(temp_contour
) rect_vertices = cv2.boxPoints(rect_tupple) rect_vertices = np.int0(
rect_vertices) if len(car_plates)==1: oldimg = cv2.drawContours(img, [
rect_vertices], -1, (0, 0, 255), 2) #cv2.imshow("che pai ding wei", oldimg) #
print(rect_tupple) break #把车牌号截取出来 if len(car_plates)==1: for car_plate in
car_plates: row_min,col_min = np.min(car_plate[:,0,:],axis=0) row_max,col_max =
np.max(car_plate[:,0,:],axis=0) cv2.rectangle(img,(row_min,col_min),(row_max,
col_max),(0,255,0),2) card_img = img[col_min:col_max,row_min:row_max,:] cv2.
imshow("img",img) cv2.imwrite(output_img + '/' + 'card_img' + '.jpg',card_img)
cv2.imshow("card_img.",card_img) cv2.waitKey(0) cv2.destroyAllWindows() return 1
return 0

技术
©2019-2020 Toolsou All rights reserved,
详解ubuntu14.04如何设置静态IPQCustomPlot系列(5)-实时动态曲线比尔·盖茨:疫情后彻底恢复正常可能要到2022年末华为认证HCIA-AI人工智能Python基础知识整理笔记百度、阿里、腾讯内部岗位级别和薪资结构,附带求职建议!Jsp+Ajax+Servlet+Mysql实现增删改查(一)2021年1月程序员工资统计,平均14915元Faster RCNN系列算法原理讲解(笔记)经典算法-递归(生兔子案例)