前言

本博客为模式识别作业的记录，实现批感知器算法、Ho Kashyap算法和MSE多类扩展方法，可参考教材[ 1 ] color{#0000FF}{[1]}[1]。所用数据如下如所示：

批感知器算法

从a = 0 mathbf a=0a=0开始迭代，分类ω 1 omega_1ω1​和ω 2 omega_2ω2​并计算最终的解向量，记录下收敛的步数。

import cv2
import numpy as np
from imutils import contours
from matplotlib import pyplot as plt

# 定义绘图函数
def imshow(name, img):
    cv2.imshow(name, img)
    cv2.waitKey(0)
    cv2.destroyAllWindows()


def num_cnts_sort(list,right=1,up=0):
    # 传入的是找到的轮廓，返回的是排序好的轮廓外接矩阵的（x,y,w,h)
    # up=1表示从上往下，right=1表示从左往右，-1表示反过来
    reverse = False
    if up==-1 or right== -1:
        reverse = True

    if up == 0:
        # 左右方向排序 权重选x
        i = 0

    if right == 0:
        i = 1

    # 找到的轮廓用外接矩形框起来 cv2.boundingRect(c)返回x,y,w,h
    boundingBoxs = [cv2.boundingRect(c) for c in list]
    # sorted(输入序列，排序规则，reverse=True由小到大否则由大到小）
    # lambda 匿名函数 输入序列的每个元素 输出b[i]
    boxs = sorted(boundingBoxs,key= lambda b: b[i],reverse=reverse )

    return boxs

def num_resize(img,w_size=0,h_size=0):
    (h,w)=img.shape[0:2] # size返回总元素个数 和matlab不一样
    if h_size != 0:
        r = h_size/float(h)
        w_size = int(r*w)
    if w_size != 0:
        r = w_size/float(w)
        h_size = int(r*h)
    resized = cv2.resize(img,(w_size,h_size))
    return resized

# 读取模板图片
img_num = cv2.imread("images/ocr_a_reference.png")
# cv2.cvtColor获得图像的副本
img_num_gray = cv2.cvtColor(img_num, cv2.COLOR_BGR2GRAY)
imshow("img_num",img_num)
# cv2.threshold(输入图像，阈值，赋值，方法） 这里方法是高于阈值取0，低于阈值取255
# cv2.threshold返回两个值 第二个值是我需要的处理后的图像
img_num_bin = cv2.threshold(img_num_gray,10,255,cv2.THRESH_BINARY_INV)[1]
imshow("img_num_bin",img_num_bin)

# 获取轮廓
# 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
num_cnts_list, _ =cv2.findContours(img_num_bin.copy(),cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_SIMPLE)

"""
cv2.drawContours(img_num, num_cnts_list, -1, (0,0,255), 2)
imshow("draw_img_num",img_num_bin)
"""
# 对轮廓排序 并且返回论廓外接矩形的坐标
num_rect_list = num_cnts_sort(num_cnts_list)

# 验证排序正确

"""
for num_rect in num_rect_list:
    (x,y,w,h)=num_rect
    num_rect_img = cv2.rectangle(img_num.copy(),(x,y),(x+w,y+h),(255,0,0),2)
    imshow("num_rect_img",num_rect_img)
"""
# 把图片和数字对应
num_rect_dic = {}
for (i,num_rect) in enumerate(num_rect_list):
    (x, y, w, h) = num_rect
    # 对图片像素点操作x,y要对调，因为dim=0存的是行 是x方向的像素信息
    num_rect_item = img_num_bin[y:y+h,x:x+w]

    num_rect_item = cv2.resize(num_rect_item,(57,88))
    # 把数字和截下来的图像对应
    num_rect_dic[i]=num_rect_item

    imshow("num_rect_item", num_rect_item)

# 对银行卡图像预处理
# 读取图像
bank_img = cv2.imread("images/credit_card_01.png")
bank_img = num_resize(bank_img,h_size=200)
bank_img_gray = cv2.cvtColor(bank_img,cv2.COLOR_BGR2GRAY)

# bank_img_gray = num_resize(bank_img_gray,h_size=200)
# bank_img = cv2.resize(bank_img,bank_img_gray.shape)
imshow("bank_img",bank_img)
imshow("bank_img_gray",bank_img_gray)

# 定义卷积核
rectKernel = cv2.getStructuringElement(cv2.MORPH_RECT, (9, 3))  # 矩形卷积核
sqKernel = cv2.getStructuringElement(cv2.MORPH_RECT,(5,5))

# 顶帽操作 突出明亮的部分
bank_img_tophat = cv2.morphologyEx(bank_img_gray,cv2.MORPH_TOPHAT, rectKernel)
imshow("bank_img_tophat",bank_img_tophat)

# 对x方向边缘检测分支 然后二值化
def branch1(bank_img_tophat):
    # X方向边缘检测处理 横线太浅 y方向边缘检测可能会消失
    bank_img_grad = cv2.Sobel(bank_img_tophat, cv2.CV_32F, 1, 0, ksize=-1)
    bank_img_grad_abs = np.absolute(bank_img_grad)
    (max, min) = (np.max(bank_img_grad_abs), np.min(bank_img_grad_abs))
    bank_img_grad_abs = (255 * (bank_img_grad_abs - min) / (max - min))
    bank_img_grad_abs = bank_img_grad_abs.astype("uint8")
    imshow("bank_img_grad_abs", bank_img_grad_abs)

    return bank_img_grad_abs


bank_img_grad_abs = branch1(bank_img_tophat)

# 腐蚀与闭操作
bank_img_close = cv2.morphologyEx(bank_img_grad_abs,cv2.MORPH_DILATE,sqKernel)
bank_img_close = cv2.morphologyEx(bank_img_close,cv2.MORPH_CLOSE,sqKernel)
imshow("bank_img_close",bank_img_close)

bank_img_close= cv2.morphologyEx(bank_img_close,cv2.MORPH_CLOSE,sqKernel)
# 二值化 cv2.THRESH_OTSU会选择合适的阈值进行二值化 cv2.threshold返回的是两个元素 第二个是处理后的图像
bank_img_close_bin = cv2.threshold(bank_img_close, 0, 255, cv2.THRESH_BINARY | cv2.THRESH_OTSU)[1]
imshow("double-close",bank_img_close_bin )

# 获取轮廓
bank_img_gray1 = bank_img_gray.copy()
bank_img_contour,_ = cv2.findContours(bank_img_close_bin,cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_SIMPLE)
"""
cv2.drawContours(bank_img_gray,bank_img_contour,-1,(0,0,255),3)
imshow("contours",bank_img_gray)
"""


# 通过以下代码找到一组银行卡上的轮廓 计算大概的比例和长度
"""
(x,y,w,h) = cv2.boundingRect(bank_img_contour[4])
bank_img_draw = bank_img_gray
bank_img_draw = cv2.rectangle(bank_img_draw,(x,y),(x+w,y+h),(0,0,255),2)
imshow("1",bank_img_draw)
print("w="+str(w)+"h="+str(h),"r="+str(w/float(h)))
"""


# 获取轮廓外接矩形 并过滤不合格的轮廓
bank_img_real_contour=[]
for contour in bank_img_contour:
    (x, y, w, h) = cv2.boundingRect(contour)
    r = w / float(h)
    if r > 2.5 and r < 4.0:
        if w > 50 and w < 80 and h > 10 and h < 30:
            bank_img_real_contour.append(contour)
            # 画出来看看
            img_draw = cv2.cvtColor(bank_img,1)
            bank_draw = cv2.rectangle(img_draw, (x, y), (x + w, y + h), (0, 128, 128), 2)
            imshow("s", bank_draw)

# 4个一组 获取对应二值图像
bank_img_list = []
# 把4组从左往右排序 返回每组的（x,y,w,h)
contour_list = num_cnts_sort(bank_img_real_contour)
for contour in contour_list:
    (x, y, w, h) = contour
    # 把每组的灰度图像填充5个像素截取下来
    bank_img = bank_img_gray[(y - 5):(y + 5 + h), (x - 5):(x + 5 + w)]
    # 二值化
    bank_img = cv2.threshold(bank_img, 0, 255, cv2.THRESH_BINARY | cv2.THRESH_OTSU)[1]
    imshow("bank_img", bank_img)
    bank_img_list.append(bank_img)

# 获取每个数字进行模板匹配
grade = []
for img in bank_img_list:
    # 对包含4个数字的图片进行轮廓检测
    bank_contours, _ = cv2.findContours(img, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
    # 对每个数字排序 返回的是每个轮廓外接矩形的（x,y,w,h)
    bank_cont_rec = num_cnts_sort(bank_contours)

    for i, rec in enumerate(bank_cont_rec):
        (x, y, w, h) = rec
        num = img[y:(y + h), x:(x + w)]
        # 缩放到和模板一样大小
        roi = cv2.resize(num, (57, 88))

        item = 0
        # 字典num_rect_dic存有数字和对应图像
        for num in range(10):
            # 模板匹配
            num_img = num_rect_dic[num]
            # 模板匹配
            result = cv2.matchTemplate(roi, num_img, cv2.TM_CCOEFF)
            (_, score, _, _) = cv2.minMaxLoc(result)
            # 记下最大值，最贴近正确值得对应的 num
            if score > item:
                item = score
                max = num

        grade.append(str(max))
# cv2.putText(图像, 文字, 左下角坐标, 字体, 大小, 颜色, 字体粗细)
cv2.putText(img_draw, "".join(grade), (contour_list[0][0], contour_list[0][1] - 15), cv2.FONT_HERSHEY_PLAIN, 1,
            (0, 255, 0), 1)

imshow("bank", img_draw)

# .join把序列的字符串和前面的拼在一起
print("银行卡号为" + "".join(grade))