python基于OpenCV模板匹配識(shí)別圖片中的數(shù)字

def cv_show(name, img):
 cv2.imshow(name, img)
 cv2.waitKey(0)
 cv2.destroyAllWindows()

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

if __name__ == "__main__":
 # 存放數(shù)字模板列表
 digits = []
 # 當(dāng)前運(yùn)行目錄
 now_dir = os.getcwd()
 print("當(dāng)前運(yùn)行目錄：" + now_dir)
 numbers_address = now_dir + "\\numbers"
 load_digits()
 times = input("請(qǐng)輸入程序運(yùn)行次數(shù)：")
 for i in range(1, int(times) + 1):
  demo(i)
 print("輸出成功，請(qǐng)檢查本地temp.txt文件")
 while True:
  if input("輸入小寫(xiě)‘q'并回車退出") == 'q':
   break

def load_digits():
 # 加載數(shù)字模板
 path = numbers_address # 這個(gè)地方就是獲取當(dāng)前運(yùn)行目錄 獲取函數(shù)在主函數(shù)里面
 filename = os.listdir(path) # 獲取文件夾文件
 for file in filename:
  img = cv2.imread(numbers_address + "\\" + file) # 讀取圖片
  img_gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) # 灰度處理
  # 自動(dòng)閾值二值化 把圖片處理成黑底白字
  img_temp = cv2.threshold(img_gray, 0, 255, cv2.THRESH_BINARY_INV | cv2.THRESH_OTSU)[1]
  # 尋找數(shù)字輪廓
  cnt = cv2.findContours(img_temp, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)[0]
  # 獲取數(shù)字矩形輪廓
  x, y, w, h = cv2.boundingRect(cnt[0])
  # 將單個(gè)數(shù)字區(qū)域進(jìn)行縮放并存到列表中以備后面使用
  digit_roi = cv2.resize(img_temp[y:y+h, x:x+w], (57, 88))
  digits.append(digit_roi)

 # 這兩個(gè)都是核，參數(shù)可以改變
 rectKernel = cv2.getStructuringElement(cv2.MORPH_RECT, (25, 25))
 sqKernel = cv2.getStructuringElement(cv2.MORPH_RECT, (5, 5))
 # 這個(gè)就是讀取圖片的，可以暫時(shí)不理解
 target_path = now_dir + "\\" + "demo_" + str(index) + ".png"
 img_origin = cv2.imread(target_path)
 # 對(duì)圖片進(jìn)行縮放處理
 img_origin = resize(img_origin, width=300)
 # 灰度圖
 img_gray = cv2.cvtColor(img_origin, cv2.COLOR_BGR2GRAY)
 # 高斯濾波 參數(shù)可以改變，選擇效果最好的就可以
 gaussian = cv2.GaussianBlur(img_gray, (5, 5), 1)、
 # 自動(dòng)二值化處理，黑底白字
 img_temp = cv2.threshold(
  gaussian, 0, 255, cv2.THRESH_BINARY_INV | cv2.THRESH_OTSU)[1]
 # 頂帽操作
 img_top = cv2.morphologyEx(img_temp, cv2.MORPH_TOPHAT, rectKernel)
 # sobel操作
 img_sobel_x = cv2.Sobel(img_top, cv2.CV_64F, 1, 0, ksize=7)
 img_sobel_x = cv2.convertScaleAbs(img_sobel_x)
 img_sobel_y = cv2.Sobel(img_top, cv2.CV_64F, 0, 1, ksize=7)
 img_sobel_y = cv2.convertScaleAbs(img_sobel_y)
 img_sobel_xy = cv2.addWeighted(img_sobel_x, 1, img_sobel_y, 1, 0)
 # 閉操作
 img_closed = cv2.morphologyEx(img_sobel_xy, cv2.MORPH_CLOSE, rectKernel)
 # 自動(dòng)二值化
 thresh = cv2.threshold(
  img_closed, 0, 255, cv2.THRESH_BINARY | cv2.THRESH_OTSU)[1]
 # 閉操作
 img_closed = cv2.morphologyEx(thresh, cv2.MORPH_CLOSE, sqKernel)
 # 尋找數(shù)字輪廓
 cnts = cv2.findContours(
  img_closed.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)[0]
 # 輪廓排序
 (cnts, boundingBoxes) = contours.sort_contours(cnts, "top-to-bottom")
 # 存放正確數(shù)字序列（包含逗號(hào)）的輪廓，即過(guò)濾掉不需要的輪廓
 right_loc = []
 # 下面這個(gè)循環(huán)是對(duì)輪廓進(jìn)行篩選，只有長(zhǎng)寬比例大于2的才可以被添加到列表中
 # 這個(gè)比例可以根據(jù)具體情況來(lái)改變。除此之外，還可以通過(guò)輪廓周長(zhǎng)和輪廓面積等對(duì)輪廓進(jìn)行篩選
 for c in cnts:
  x, y, w, h = cv2.boundingRect(c)
  ar = w/float(h)
  if ar > 2:
   right_loc.append((x, y, w, h))

for (gx, gy, gw, gh) in right_loc:
  # 用于存放識(shí)別到的數(shù)字
  digit_out = []
  # 下面兩個(gè)判斷主要是防止出現(xiàn)越界的情況發(fā)生，如果發(fā)生的話圖片讀取會(huì)出錯(cuò)
  if (gy-10  0):
   now_gy = gy
  else:
   now_gy = gy-10
  if (gx - 10  0):
   now_gx = gx
  else:
   now_gx = gx-10
  # 選擇圖片興趣區(qū)域
  img_digit = gaussian[now_gy:gy+gh+10, now_gx:gx+gw+10]
  # 二值化處理
  img_thresh = cv2.threshold(
   img_digit, 0, 255, cv2.THRESH_BINARY_INV | cv2.THRESH_OTSU)[1]
  # 尋找所有輪廓 找出每個(gè)數(shù)字的輪廓（包含逗號(hào)） 正確的話應(yīng)該有9個(gè)輪廓
  digitCnts = cv2.findContours(
   img_thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)[0]
  # 從左到右排列輪廓
  # 這樣排列的好處是，正常情況下可以確定逗號(hào)的位置方便后面刪除逗號(hào)
  (cnts, boundingBoxes) = contours.sort_contours(digitCnts, "left-to-right")
  # cnts是元組，需要先轉(zhuǎn)換成列表，因?yàn)楹竺鏁?huì)對(duì)元素進(jìn)行刪除處理
  cnts = list(cnts)
  flag = 0
  # 判斷輪廓數(shù)量是否有9個(gè)
  if len(cnts) == 9:
   # 刪除逗號(hào)位置
   del cnts[1]
   del cnts[2]
   del cnts[3]
   del cnts[4]
   # 可以在轉(zhuǎn)成元組
   cnts = tuple(cnts)
   # 存放單個(gè)數(shù)字的矩形區(qū)域
   num_roi = []
   for c in cnts:
    x, y, w, h = cv2.boundingRect(c)
    num_roi.append((x, y, w, h))
   # 對(duì)數(shù)字區(qū)域進(jìn)行處理，把尺寸縮放到與數(shù)字模板相同
   # 對(duì)其進(jìn)行簡(jiǎn)單處理，方便與模板匹配，增加匹配率
   for (rx, ry, rw, rh) in num_roi:
    roi = img_digit[ry:ry+rh, rx:rx+rw]
    roi = cv2.resize(roi, (57, 88))
    # 高斯濾波
    roi = cv2.GaussianBlur(roi, (5, 5), 1)
    # 二值化
    roi = cv2.threshold(
     roi, 0, 255, cv2.THRESH_BINARY_INV | cv2.THRESH_OTSU)[1]
    # 用于存放匹配率
    source = []
    # 遍歷數(shù)字模板
    for digitROI in digits:
     # 進(jìn)行模板匹配
     res = cv2.matchTemplate(
      roi, digitROI, cv2.TM_CCOEFF_NORMED)
     max_val = cv2.minMaxLoc(res)[1]
     source.append(max_val)
    # 這個(gè)需要仔細(xì)理解 這個(gè)就是把0-9數(shù)字中匹配度最高的數(shù)字存放到列表中
    digit_out.append(str(source.index(max(source))))
   # 打印最終輸出值
   print(digit_out)
  else:
   print("讀取失敗")
   flag = 1
  # 將數(shù)字輸出到txt文本中
  t = ''
  with open(now_dir + "\\temp.txt", 'a+') as q:
   if flag == 0:
    for content in digit_out:
     t = t + str(content) + " "
    q.write(t.strip(" "))
    q.write('\n')
    t = ''
   else:
    q.write("讀取失敗")
    q.write('\n')

from imutils import contours
import cv2
import os


def cv_show(name, img):
 cv2.imshow(name, img)
 cv2.waitKey(0)
 cv2.destroyAllWindows()


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


def load_digits():
 # 加載數(shù)字模板
 path = numbers_address
 filename = os.listdir(path)
 for file in filename:
  # print(file)
  img = cv2.imread(
   numbers_address + "\\" + file)
  img_gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
  img_temp = cv2.threshold(
   img_gray, 0, 255, cv2.THRESH_BINARY_INV | cv2.THRESH_OTSU)[1]
  cnt = cv2.findContours(img_temp, cv2.RETR_EXTERNAL,
        cv2.CHAIN_APPROX_NONE)[0]
  x, y, w, h = cv2.boundingRect(cnt[0])
  digit_roi = cv2.resize(img_temp[y:y+h, x:x+w], (57, 88))
  # 將數(shù)字模板存到列表中
  digits.append(digit_roi)


def demo(index):
 rectKernel = cv2.getStructuringElement(cv2.MORPH_RECT, (25, 25))
 sqKernel = cv2.getStructuringElement(cv2.MORPH_RECT, (5, 5))
 target_path = now_dir + "\\" + "demo_" + str(index) + ".png"
 img_origin = cv2.imread(target_path)
 img_origin = resize(img_origin, width=300)
 img_gray = cv2.cvtColor(img_origin, cv2.COLOR_BGR2GRAY)
 gaussian = cv2.GaussianBlur(img_gray, (5, 5), 1)
 img_temp = cv2.threshold(
  gaussian, 0, 255, cv2.THRESH_BINARY_INV | cv2.THRESH_OTSU)[1]
 img_top = cv2.morphologyEx(img_temp, cv2.MORPH_TOPHAT, rectKernel)
 img_sobel_x = cv2.Sobel(img_top, cv2.CV_64F, 1, 0, ksize=7)
 img_sobel_x = cv2.convertScaleAbs(img_sobel_x)
 img_sobel_y = cv2.Sobel(img_top, cv2.CV_64F, 0, 1, ksize=7)
 img_sobel_y = cv2.convertScaleAbs(img_sobel_y)
 img_sobel_xy = cv2.addWeighted(img_sobel_x, 1, img_sobel_y, 1, 0)
 img_closed = cv2.morphologyEx(img_sobel_xy, cv2.MORPH_CLOSE, rectKernel)
 thresh = cv2.threshold(
  img_closed, 0, 255, cv2.THRESH_BINARY | cv2.THRESH_OTSU)[1]
 img_closed = cv2.morphologyEx(thresh, cv2.MORPH_CLOSE, sqKernel)
 cnts = cv2.findContours(
  img_closed.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)[0]
 (cnts, boundingBoxes) = contours.sort_contours(cnts, "top-to-bottom")
 draw_img = img_origin.copy()
 draw_img = cv2.drawContours(draw_img, cnts, -1, (0, 0, 255), 1)
 cv_show("666", draw_img)

 # 存放正確數(shù)字序列（包含逗號(hào)）的輪廓，即過(guò)濾掉不需要的輪廓
 right_loc = []
 for c in cnts:
  x, y, w, h = cv2.boundingRect(c)
  ar = w/float(h)
  if ar > 2:
   right_loc.append((x, y, w, h))
 for (gx, gy, gw, gh) in right_loc:
  # 用于存放識(shí)別到的數(shù)字
  digit_out = []
  if (gy-10  0):
   now_gy = gy
  else:
   now_gy = gy-10
  if (gx - 10  0):
   now_gx = gx
  else:
   now_gx = gx-10
  img_digit = gaussian[now_gy:gy+gh+10, now_gx:gx+gw+10]
  # 二值化處理
  img_thresh = cv2.threshold(
   img_digit, 0, 255, cv2.THRESH_BINARY_INV | cv2.THRESH_OTSU)[1]
  # 尋找輪廓 找出每個(gè)數(shù)字的輪廓（包含逗號(hào)） 正確的話應(yīng)該有9個(gè)輪廓
  digitCnts = cv2.findContours(
   img_thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)[0]
  # 從左到右排列
  (cnts, boundingBoxes) = contours.sort_contours(digitCnts, "left-to-right")
  cnts = list(cnts)
  flag = 0
  if len(cnts) == 9:
   del cnts[1]
   del cnts[2]
   del cnts[3]
   del cnts[4]
   cnts = tuple(cnts)
   num_roi = []
   for c in cnts:
    x, y, w, h = cv2.boundingRect(c)
    num_roi.append((x, y, w, h))
   for (rx, ry, rw, rh) in num_roi:
    roi = img_digit[ry:ry+rh, rx:rx+rw]
    roi = cv2.resize(roi, (57, 88))
    roi = cv2.GaussianBlur(roi, (5, 5), 1)
    roi = cv2.threshold(
     roi, 0, 255, cv2.THRESH_BINARY_INV | cv2.THRESH_OTSU)[1]
    source = []
    for digitROI in digits:
     res = cv2.matchTemplate(
      roi, digitROI, cv2.TM_CCOEFF_NORMED)
     max_val = cv2.minMaxLoc(res)[1]
     source.append(max_val)
    digit_out.append(str(source.index(max(source))))
   cv2.rectangle(img_origin, (gx-5, gy-5),
       (gx+gw+5, gy+gh+5), (0, 0, 255), 1)
   print(digit_out)
  else:
   print("讀取失敗")
   flag = 1
  t = ''
  with open(now_dir + "\\temp.txt", 'a+') as q:
   if flag == 0:
    for content in digit_out:
     t = t + str(content) + " "
    q.write(t.strip(" "))
    q.write('\n')
    t = ''
   else:
    q.write("讀取失敗")
    q.write('\n')


if __name__ == "__main__":
 # 存放數(shù)字模板列表
 digits = []
 # 當(dāng)前運(yùn)行目錄
 now_dir = os.getcwd()
 print("當(dāng)前運(yùn)行目錄：" + now_dir)
 numbers_address = now_dir + "\\numbers"
 load_digits()
 times = input("請(qǐng)輸入程序運(yùn)行次數(shù)：")
 for i in range(1, int(times) + 1):
  demo(i)
 print("輸出成功，請(qǐng)檢查本地temp.txt文件")
 cv2.waitKey(0)
 cv2.destroyAllWindows()
 while True:
  if input("輸入小寫(xiě)‘q'并回車退出") == 'q':
   break