参考教程:唐宇迪老师: https://www.bilibili.com/video/BV1tb4y1C7j7
1.参数配置:
step1:
step2:找到Edit Configurations…
step3:找到Parameters一栏
step4:编辑图片、模板的路径(不要有中文,不要有空格)
2.程序代码:
myutils模块部分:
import cv2
def sort_contours(cnts, method="left-to-right"):
reverse = False
i = 0
if method == "right-to-left" or method == "bottom-to-top":
reverse = True
if method == "top-to-bottom" or method == "bottom-to-top":
i = 1
#左上角横坐标的大小
#cv2.boundingRect(c)返回四个值,x,y,h,w
boundingBoxes = [cv2.boundingRect(c) for c in cnts] #用一个最小的矩形,把找到的形状包起来x,y,h,w
(cnts, boundingBoxes) = zip(*sorted(zip(cnts, boundingBoxes),
key=lambda b: b[1][i], reverse=reverse)) #reverse = True 降序 , reverse = False 升序(默认),b[1][0]按x坐标排序
return cnts, boundingBoxes
def resize(image, width=None, height=None, inter=cv2.INTER_AREA): #cv2.INTER_AREA 基于局部像素的重采样
dim = None
(h, w) = image.shape[:2]
if width is None and height is None:
return image
if width is None:
r = height / float(h)
dim = (int(w * r), height)
else:
r = width / float(w)
dim = (width, int(h * r))
resized = cv2.resize(image, dim, interpolation=inter) #resize函数的参数dsize的形状是(w,h)
return resized
工作程序部分:
# 导入工具包
from imutils import contours
import numpy as np
import argparse
import cv2
import myutils
# 设置参数
ap = argparse.ArgumentParser() #argparse 模块可以让人轻松编写用户友好的命令行接口
ap.add_argument("-i", "--image", required=True,
help="path to input image")
ap.add_argument("-t", "--template", required=True,
help="path to template OCR-A image")
args = vars(ap.parse_args()) #vars() 函数返回对象的属性和属性值的字典对象
print(args) #键值对{'image': 'D:\\openCV_files\\data\\3\\credit_card_01.png', 'template': 'D:\\openCV_files\\data\\3\\ocr_a_reference.png'}
# 指定信用卡类型
FIRST_NUMBER = {
"3": "American Express",
"4": "Visa",
"5": "MasterCard",
"6": "Discover Card"
}
# 绘图展示
def cv_show(name,img):
cv2.imshow(name, img)
cv2.waitKey(0)
cv2.destroyAllWindows()
# 读取一个模板图像
img = cv2.imread(args["template"])
cv_show('img',img)
# 灰度图
ref = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
cv_show('ref',ref)
# 二值图像
ref = cv2.threshold(ref, 10, 255, cv2.THRESH_BINARY_INV)[1] #cv2.threshold返回两个——阈值和输出图像,取输出图形所以[1]
cv_show('ref',ref)
# 计算轮廓
#cv2.findContours()函数接受的参数为二值图,即黑白的(不是灰度图),cv2.RETR_EXTERNAL只检测外轮廓,cv2.CHAIN_APPROX_SIMPLE只保留终点坐标
#返回的list中每个元素都是图像中的一个轮廓
refCnts, hierarchy = cv2.findContours(ref.copy(), cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_SIMPLE)
#ref后面还要用,所以copy一下
#RETR_EXTERNAL:只检索最外面的轮廓
#画轮廓
cv2.drawContours(img,refCnts,-1,(0,0,255),3) #红色,粗细度3
cv_show('img',img)
print (np.array(refCnts).shape) #打印发现十个轮廓
refCnts = myutils.sort_contours(refCnts, method="left-to-right")[0] #排序,从左到右,从上到下
digits = {} #建立一个空字典,存放模板
# 遍历每一个轮廓
for (i, c) in enumerate(refCnts): #i是轮廓的索引,c是对应的轮廓
# 计算外接矩形并且resize成合适大小
(x, y, w, h) = cv2.boundingRect(c)
roi = ref[y:y + h, x:x + w]
roi = cv2.resize(roi, (57, 88))
# 每一个数字对应每一个模板
digits[i] = roi
# 初始化卷积核
rectKernel = cv2.getStructuringElement(cv2.MORPH_RECT, (9, 3))
sqKernel = cv2.getStructuringElement(cv2.MORPH_RECT, (5, 5))
#读取输入图像,预处理
image = cv2.imread(args["image"])
cv_show('image',image)
image = myutils.resize(image, width=300)
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
cv_show('gray',gray)
#礼帽操作,突出更明亮的区域
tophat = cv2.morphologyEx(gray, cv2.MORPH_TOPHAT, rectKernel)
cv_show('tophat',tophat)
#
gradX = cv2.Sobel(tophat, ddepth=cv2.CV_32F, dx=1, dy=0, #ksize=-1相当于用3*3的 ,cv2.CV_32F表示32位浮点数即32float
ksize=-1)
#加绝对值,白到黑,黑到白的边界都可以检测到
#实验发现,只用x,比x,y都用,效果更好
gradX = np.absolute(gradX)
#将边界归一化处理,看的更清楚
(minVal, maxVal) = (np.min(gradX), np.max(gradX))
gradX = (255 * ((gradX - minVal) / (maxVal - minVal)))
#转化为8位无符号数
gradX = gradX.astype("uint8")
print (np.array(gradX).shape)
cv_show('gradX',gradX)
#通过闭操作(先膨胀,再腐蚀)将数字连在一起
gradX = cv2.morphologyEx(gradX, cv2.MORPH_CLOSE, rectKernel)
cv_show('gradX',gradX)
#THRESH_OTSU会自动寻找合适的阈值,适合双峰,需把阈值参数设置为0
thresh = cv2.threshold(gradX, 0, 255,
cv2.THRESH_BINARY | cv2.THRESH_OTSU)[1]
cv_show('thresh',thresh)
#再来一个闭操作
#把分割好的四字区域填充完整
thresh = cv2.morphologyEx(thresh, cv2.MORPH_CLOSE, sqKernel) #再来一个闭操作
cv_show('thresh',thresh)
# 计算轮廓
threshCnts, hierarchy = cv2.findContours(thresh.copy(), cv2.RETR_EXTERNAL,
cv2.CHAIN_APPROX_SIMPLE)
cnts = threshCnts
cur_img = image.copy()
cv2.drawContours(cur_img,cnts,-1,(0,0,255),3)
cv_show('img',cur_img)
locs = []
# 遍历轮廓,筛选出想要的轮廓
for (i, c) in enumerate(cnts):
# 计算矩形
(x, y, w, h) = cv2.boundingRect(c)
ar = w / float(h)
# 选择合适的区域,根据实际任务来,这里的基本都是四个数字一组
if ar > 2.5 and ar < 4.0:
if (w > 40 and w < 55) and (h > 10 and h < 20):
#符合的留下来
locs.append((x, y, w, h))
# 将符合的轮廓从左到右排序
locs = sorted(locs, key=lambda x:x[0])
output = [] #建立一个存储结果的空列表
# 遍历每一个轮廓中的数字
for (i, (gX, gY, gW, gH)) in enumerate(locs):
# initialize the list of group digits
groupOutput = []
# 根据坐标提取每一个组
group = gray[gY - 5:gY + gH + 5, gX - 5:gX + gW + 5] #适当变大一些些
cv_show('group',group)
# 预处理
group = cv2.threshold(group, 0, 255,
cv2.THRESH_BINARY | cv2.THRESH_OTSU)[1]
cv_show('group',group)
# 计算每一组的轮廓
digitCnts,hierarchy = cv2.findContours(group.copy(), cv2.RETR_EXTERNAL,
cv2.CHAIN_APPROX_SIMPLE)
digitCnts = contours.sort_contours(digitCnts,
method="left-to-right")[0]
# 计算每一组中的每一个数值
for c in digitCnts:
# 找到当前数值的轮廓,resize成合适的的大小
(x, y, w, h) = cv2.boundingRect(c)
roi = group[y:y + h, x:x + w]
roi = cv2.resize(roi, (57, 88)) #与上面的模板大小相同(57,88)
cv_show('roi',roi)
# 计算匹配得分
scores = []
# 在模板中计算每一个得分
for (digit, digitROI) in digits.items():
# 模板匹配
result = cv2.matchTemplate(roi, digitROI,
cv2.TM_CCOEFF)#TM_CCOEFF:计算相关系数,计算出来的值越大,越相关
(_, score, _, _) = cv2.minMaxLoc(result)
scores.append(score)
# 得到最合适的数字
groupOutput.append(str(np.argmax(scores)))
# 画出来
cv2.rectangle(image, (gX - 5, gY - 5),
(gX + gW + 5, gY + gH + 5), (0, 0, 255), 1)
cv2.putText(image, "".join(groupOutput), (gX, gY - 15),
cv2.FONT_HERSHEY_SIMPLEX, 0.65, (0, 0, 255), 2)
# 得到结果
output.extend(groupOutput) #extend() 函数用于在列表末尾一次性追加另一个序列中的多个值
# 打印结果
print("Credit Card Type: {}".format(FIRST_NUMBER[output[0]]))
print("Credit Card #: {}".format("".join(output)))
cv2.imshow("Image", image)
cv2.waitKey(0)
3.打印输出:
{'image': 'D:\\openCV_files\\data\\3\\credit_card_01.png', 'template': 'D:\\openCV_files\\data\\3\\ocr_a_reference.png'}
(10,)
D:\PyCharm files\openCV\项目实战\信用卡数字识别\ocr_template_match.py:50: VisibleDeprecationWarning: Creating an ndarray from ragged nested sequences (which is a list-or-tuple of lists-or-tuples-or ndarrays with different lengths or shapes) is deprecated. If you meant to do this, you must specify 'dtype=object' when creating the ndarray.
print (np.array(refCnts).shape) #打印发现十个轮廓
(189, 300)
Credit Card Type: Visa
Credit Card #: 4000123456789010