前言

本博客為模式識別作業的記錄，實作批感知器演算法、Ho Kashyap演算法和MSE多類擴展方法，可參考教材[ 1 ] \color{#0000FF}{[1]}[1]，所用資料如下如所示：

批感知器演算法

從a = 0 \mathbf a=0a=0開始迭代，分類ω 1 \omega_1ω1?和ω 2 \omega_2ω2?并計算最終的解向量，記錄下收斂的步數，

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

# 定義繪圖函式
def imshow(name, img):
    cv2.imshow(name, img)
    cv2.waitKey(0)
    cv2.destroyAllWindows()


def num_cnts_sort(list,right=1,up=0):
    # 傳入的是找到的輪廓，回傳的是排序好的輪廓外接矩陣的（x,y,w,h)
    # up=1表示從上往下，right=1表示從左往右，-1表示反過來
    reverse = False
    if up==-1 or right== -1:
        reverse = True

    if up == 0:
        # 左右方向排序 權重選x
        i = 0

    if right == 0:
        i = 1

    # 找到的輪廓用外接矩形框起來 cv2.boundingRect(c)回傳x,y,w,h
    boundingBoxs = [cv2.boundingRect(c) for c in list]
    # sorted(輸入序列，排序規則，reverse=True由小到大否則由大到小）
    # lambda 匿名函式 輸入序列的每個元素 輸出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回傳總元素個數 和matlab不一樣
    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

# 讀取模板圖片
img_num = cv2.imread('images/ocr_a_reference.png')
# cv2.cvtColor獲得影像的副本
img_num_gray = cv2.cvtColor(img_num, cv2.COLOR_BGR2GRAY)
imshow('img_num',img_num)
# cv2.threshold(輸入影像，閾值，賦值，方法） 這里方法是高于閾值取0，低于閾值取255
# cv2.threshold回傳兩個值 第二個值是我需要的處理后的影像
img_num_bin = cv2.threshold(img_num_gray,10,255,cv2.THRESH_BINARY_INV)[1]
imshow('img_num_bin',img_num_bin)

# 獲取輪廓
# cv2.findContours()函式接受的引數為二值圖，即黑白的（不是灰度圖）,cv2.RETR_EXTERNAL只檢測外輪廓，cv2.CHAIN_APPROX_SIMPLE只保留終點坐標
# 回傳的list中每個元素都是影像中的一個輪廓
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)
'''
# 對輪廓排序 并且回傳論廓外接矩形的坐標
num_rect_list = num_cnts_sort(num_cnts_list)

# 驗證排序正確

'''
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)
'''
# 把圖片和數字對應
num_rect_dic = {}
for (i,num_rect) in enumerate(num_rect_list):
    (x, y, w, h) = num_rect
    # 對圖片像素點操作x,y要對調，因為dim=0存的是行 是x方向的像素資訊
    num_rect_item = img_num_bin[y:y+h,x:x+w]

    num_rect_item = cv2.resize(num_rect_item,(57,88))
    # 把數字和截下來的影像對應
    num_rect_dic[i]=num_rect_item

    imshow('num_rect_item', num_rect_item)

# 對銀行卡影像預處理
# 讀取影像
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)

# 定義卷積核
rectKernel = cv2.getStructuringElement(cv2.MORPH_RECT, (9, 3))  # 矩形卷積核
sqKernel = cv2.getStructuringElement(cv2.MORPH_RECT,(5,5))

# 頂帽操作 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)

# 對x方向邊緣檢測分支 然后二值化
def branch1(bank_img_tophat):
    # X方向邊緣檢測處理 橫線太淺 y方向邊緣檢測可能會消失
    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)

# 腐蝕與閉操作
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會選擇合適的閾值進行二值化 cv2.threshold回傳的是兩個元素 第二個是處理后的影像
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 )

# 獲取輪廓
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)
'''


# 通過以下代碼找到一組銀行卡上的輪廓 計算大概的比例和長度
'''
(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)))
'''


# 獲取輪廓外接矩形 并過濾不合格的輪廓
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)
            # 畫出來看看
            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個一組 獲取對應二值影像
bank_img_list = []
# 把4組從左往右排序 回傳每組的（x,y,w,h)
contour_list = num_cnts_sort(bank_img_real_contour)
for contour in contour_list:
    (x, y, w, h) = contour
    # 把每組的灰度影像填充5個像素截取下來
    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)

# 獲取每個數字進行模板匹配
grade = []
for img in bank_img_list:
    # 對包含4個數字的圖片進行輪廓檢測
    bank_contours, _ = cv2.findContours(img, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
    # 對每個數字排序 回傳的是每個輪廓外接矩形的（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)]
        # 縮放到和模板一樣大小
        roi = cv2.resize(num, (57, 88))

        item = 0
        # 字典num_rect_dic存有數字和對應影像
        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)
            # 記下最大值，最貼近正確值得對應的 num
            if score > item:
                item = score
                max = num

        grade.append(str(max))
# cv2.putText(影像, 文字, 左下角坐標, 字體, 大小, 顏色, 字體粗細)
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把序列的字串和前面的拼在一起
print('銀行卡號為' + ''.join(grade))

標籤：Python

上一篇：虛函式&虛繼承

下一篇：虛函式&虛繼承