实战项目:信用卡号识别
0、导入模块
导入相关函数,遇到报错的话,直接pip install 函数名。
from imutils import contours
import numpy as np
import argparse
import cv2
import myutils
myutils函数代码
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
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))
return cnts, boundingBoxes
def resize(image, width=None, height=None, inter=cv2.INTER_AREA):
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)
return resized
参数初始化
ap = argparse.ArgumentParser()
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())
后面代码运行前,先设置好参数(Edit Configurations)
Parameters:
--image images\credit_card_01.png --template images\ocr_a_reference.png
1、制作模板
读取模板图片,进行灰度、二值化,提取轮廓,一个轮廓对应一个模板
img = cv2.imread(args["template"])
ref = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)#灰度化
ref = cv2.threshold(ref, 10, 255, cv2.THRESH_BINARY_INV)[1]#大于10的像素点设为0,其余设为255
#只检测外轮廓,只保留终点坐标,refCnts是一个list,保存轮廓信息
refCnts, hierarchy = cv2.findContours(ref.copy(), cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_SIMPLE)
cv2.drawContours(img,refCnts,-1,(0,0,255),3) #把轮廓画出
refCnts = myutils.sort_contours(refCnts, method="left-to-right")[0] #排序,从左到右,从上到下
# 遍历每一个轮廓
digits = {}
for (i, c) in enumerate(refCnts):
# 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)
digits[i] = roi# 每一个数字对应每一个模板
2、目标图片预处理
读取目标图片、灰度化、礼帽操作、Sobel算子提取轮廓、闭操作、自动阈值、再次闭操作
# 初始化卷积核
rectKernel = cv2.getStructuringElement(cv2.MORPH_RECT, (9, 3))
sqKernel = cv2.getStructuringElement(cv2.MORPH_RECT, (5, 5))
image = cv2.imread(args["image"])
image = myutils.resize(image, width=300)
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
#礼帽操作,突出更明亮的区域
tophat = cv2.morphologyEx(gray, cv2.MORPH_TOPHAT, rectKernel)
#Sobel算子提取轮廓
gradX = cv2.Sobel(tophat, ddepth=cv2.CV_32F, dx=1, dy=0, #ksize=-1相当于用3*3的
ksize=-1)
gradX = np.absolute(gradX)
(minVal, maxVal) = (np.min(gradX), np.max(gradX))
gradX = (255 * ((gradX - minVal) / (maxVal - minVal)))
gradX = gradX.astype("uint8")
#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)
#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]
thresh = cv2.morphologyEx(thresh, cv2.MORPH_CLOSE, sqKernel) #再来一个闭操作
3、筛查侯选目标轮廓
遍历所有轮廓,进行筛查
# 计算轮廓
threshCnts, hierarchy = cv2.findContours(thresh.copy(), cv2.RETR_EXTERNAL,
cv2.CHAIN_APPROX_SIMPLE)
cnts = threshCnts
# 遍历轮廓
locs = []
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))
locs = sorted(locs, key=lambda x:x[0])# 将符合的轮廓从左到右排序
4、识别目标轮廓
依次对每一个目标轮廓进行识别,首先遍历每一个轮廓中的数字,与模板进行匹配并计算的得分,得分高的模板为识别结果。
# 遍历每一个轮廓中的数字
output = []
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]
# 预处理
group = cv2.threshold(group, 0, 255,
cv2.THRESH_BINARY | cv2.THRESH_OTSU)[1]
# 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))
# 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)
(_, score, _, _) = cv2.minMaxLoc(result)
scores.append(score)
# 得到最合适的数字
groupOutput.append(str(np.argmax(scores)))
#绘图
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)
output.extend(groupOutput)# 得到结果