总目录
图像处理总目录←点击这里
十四、信用卡数字识别
- 识别的图片
- 模板图片
14.1、模板图片处理
读入图片->灰度图->二值图->计算轮廓->存储每一个模板
如果是所需模板匹配只有一个,课直接读入灰度图像即可
这里有10个模板(0-9),所以需要切割存储为多个模板进行循环匹配
# 预处理
# 读入图片->灰度图->二值图->计算轮廓->存储每一个模板
# 遍历模板的每一个轮廓并且存储
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))
# 每一个数字对应每一个模板
digits[i] = roi
14.2、识别图片处理
读取图像->灰度->礼帽(去除背景)->梯度(边界)->闭操作(先膨胀,再腐蚀)-找阈值->闭操作->计算轮廓->遍历筛选(宽高比)存储->再次计算轮廓(每个小部分,如4000)
灰度
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
礼帽
rectKernel = cv2.getStructuringElement(cv2.MORPH_RECT, (9, 3))
tophat = cv2.morphologyEx(gray, cv2.MORPH_TOPHAT, rectKernel)
梯度
sobel算子梯度
gradX = cv2.Sobel(tophat, ddepth=cv2.CV_32F, dx=1, dy=0, ksize=-1) # ksize=-1相当于用3*3的
gradX = np.absolute(gradX)
(minVal, maxVal) = (np.min(gradX), np.max(gradX))
gradX = (255 * ((gradX - minVal) / (maxVal - minVal)))
gradX = gradX.astype("uint8")
闭操作
gradX = cv2.morphologyEx(gradX, cv2.MORPH_CLOSE, rectKernel)
找阈值
这里采用双峰自动找合适的阈值,以下为固定写法
thresh = cv2.threshold(gradX, 0, 255, cv2.THRESH_BINARY | cv2.THRESH_OTSU)[1]
闭操作
让目前轮廓白色填充满
thresh = cv2.morphologyEx(thresh, cv2.MORPH_CLOSE, sqKernel)
计算轮廓
计算轮廓在原图像中展示
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)
筛选
按符合条件的比例进行筛选,筛选出符合条件的
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))
再次计算轮廓并处理
遍历上面每一个轮廓中的数字并且和模板匹配
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]
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))
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)
(_, 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)
最终效果
原图
源码
主程序
注意初始化参数的输入
--image ./images/credit_card_01.png --template ocr_a_reference.png
# 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()
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())
# 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]
# 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)
cv2.drawContours(img, refCnts, -1, (0, 0, 255), 3)
# cv_show('img', img)
print(np.array(refCnts).shape)
refCnts = myutils.sort_contours(refCnts, method="left-to-right")[0] # 排序,从左到右,从上到下
digits = {}
# 遍历每一个轮廓
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))
# 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) # ksize=-1相当于用3*3的
gradX = np.absolute(gradX)
(minVal, maxVal) = (np.min(gradX), np.max(gradX))
gradX = (255 * ((gradX - minVal) / (maxVal - minVal)))
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
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
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 = []
# 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]
# 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))
# 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)
(_, 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)
# 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)
工具方法
myutils.py
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