【Python_Opencv图像处理框架】信用卡数字识别项目

写在前面

本篇文章是opencv学习的第六篇文章，前面主要讲解了对图像的一些基本操作，这篇文章我们就开始大展身手，将前面所学的基础操作活学活用。既能复习基础操作，又能学到一些新的知识。作为初学者，我尽己所能，但仍会存在疏漏的地方，希望各位看官不吝指正🥰

写在中间

（ 1 ）简单介绍

（ 2 ）操作步骤

对模板

• 读取数字模板图像cv2.imread()

• 数字模板转换为灰度图cv2.cvtcolor()

• 灰度图转换为二值图cv2.threshold()，并实现对图像的黑白反转

• 对二值图轮廓检测cv2.findcontours()，只检测外轮廓且保存对角线上的点；

• 将轮廓从左到右依次排序contours.sort_contours()，之后遍历每一个轮廓

对目标图像

• 读取信用卡图像cv2.imread()

• 信用卡图重构大小，并转换为灰度图

• 礼帽操作cv2.morphologyex()。突出明亮的部分，过滤较暗的部分

• sobel算子边缘检测cv2.sobel()

• 闭操作（先膨胀再腐蚀）+二值化+闭操作

• 计算并画出轮廓cv2.findcontours()、cv2.drawcontours()

• 下面的操作还有很多：遍历轮廓，筛选出数字轮廓，将数字轮廓进行排序，对四组轮廓每组都灰度处理，提取数字轮廓，将数字轮廓与模板数字轮廓比对，得出数字结果，最后绘制出来，大致效果如下：

（ 3 ）代码展示

# 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()

# 轮廓排序
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

# 读取一个模板图像
img = cv2.imread("d:\python\program\pythonproject\photos\p_5_0.png")
cv_show('img', img)
# cv2.imwrite("d:\python\program\pythonproject\photos\p_5.jpg", img)

# 灰度图,颜色通道bgr to gray
ref = cv2.cvtcolor(img, cv2.color_bgr2gray)
cv_show('ref', ref)

# 二值图像(因为模板的边缘都是白色的)
ref = cv2.threshold(ref, 10, 255, cv2.thresh_binary_inv)[1]
cv_show('ref', ref)
# cv2.imwrite("d:\python\program\pythonproject\photos\p_6.jpg", 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（需要得到他的外接矩形），
# 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)
# cv2.imwrite("d:\python\program\pythonproject\photos\p_7.jpg", img)

# 轮廓排序
print(np.array(refcnts).shape)  # 打印轮廓为 (10,)
refcnts = contours.sort_contours(refcnts, method='left-to=right')[0]
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]
    # resize一下合适的大小
    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("d:\python\program\pythonproject\photos\p_8_0.png")
cv_show('image', image)
# cv2.imwrite("d:\python\program\pythonproject\photos\p_8.jpg", image)

image = resize(image, width=300)
gray = cv2.cvtcolor(image, cv2.color_bgr2gray)
cv_show('gray', gray)
# cv2.imwrite("d:\python\program\pythonproject\photos\p_9.jpg", 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)
# cv2.imwrite("d:\python\program\pythonproject\photos\p_10.jpg", tophat)


# 梯度计算：根据字体的大小进行过滤
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)
# cv2.imwrite("d:\python\program\pythonproject\photos\p_11.jpg", 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)
# cv2.imwrite("d:\python\program\pythonproject\photos\p_12.jpg", 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)
# cv2.imwrite("d:\python\program\pythonproject\photos\p_13.jpg", 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)
# cv2.imwrite("d:\python\program\pythonproject\photos\p_14.jpg", 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 = []
cv2.imwrite("d:\python\program\pythonproject\photos\p_16.jpg", cur_img)


# 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)

print("credit card type: {}".format(first_number[output[0]]))
print("credit card #: {}".format("".join(output)))
cv2.imshow("image", image)
# cv2.imwrite("d:\python\program\pythonproject\photos\p_17.jpg", image)
cv2.waitkey(0)
cv2.destroyallwindows()

写在最后