def get_roi_contours(image_path, morph_size, num_morph):
  '''
  參數(shù)詳解：
  image_path：所需處理圖片路徑
  morph_size：形態(tài)學處理核的大小
  num_morph：進行形態(tài)學處理的次數(shù)
  '''
  image = cv2.imread(image_path, cv2.IMREAD_COLOR)
  #灰度轉換
  gray_image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
  #二值化
  threhold, binary_image = cv2.threshold(gray_image, 0, 255, cv2.THRESH_BINARY_INV+cv2.THRESH_OTSU)
  #形態(tài)學操作
  kernel = cv2.getStructuringElement(shape=cv2.MORPH_RECT, ksize=morph_size)
  morph_image = cv2.morphologyEx(binary_image, cv2.MORPH_CLOSE, kernel)
  for i in range(num_morph-1):
    morph_image = cv2.morphologyEx(morph_image, cv2.MORPH_CLOSE, kernel)
  #查找輪廓
  contours, hierarchy = cv2.findContours(morph_image, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
  #選取輪廓面積最大的輪廓
  area = 0
  max_area_index = 0
  for j in range(len(contours)):
    if area < cv2.contourArea(contours[j]):
      max_area_index = j
      area = cv2.contourArea(contours[j])
  rect = cv2.boundingRect(contours[max_area_index])
  return rect

def get_roi_ConCom(image_path, morph_size, num_morph):
  '''
  參數(shù)詳解：
  image_path：所需處理圖片路徑
  morph_size：形態(tài)學處理核的大小
  num_morph：進行形態(tài)學處理的次數(shù)
  '''
  image = cv2.imread(image_path, cv2.IMREAD_COLOR)
  #灰度轉換
  gray_image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
  #二值化
  threhold, binary_image = cv2.threshold(gray_image, 0, 255, cv2.THRESH_BINARY_INV+cv2.THRESH_OTSU)
  #形態(tài)學操作
  kernel = cv2.getStructuringElement(shape=cv2.MORPH_RECT, ksize=morph_size)
  morph_image = cv2.morphologyEx(binary_image, cv2.MORPH_CLOSE, kernel)
  for i in range(num_morph-1):
    morph_image = cv2.morphologyEx(morph_image, cv2.MORPH_CLOSE, kernel)
  #聯(lián)通組件查詢
  numlabels, components_img, stats, centers = cv2.connectedComponentsWithStats(morph_image, 8)
  #獲取除背景外的所有聯(lián)通組件
  stats_without_back = stats[1:]
  #獲取除背景外的所有聯(lián)通組件的面積最大值
  max_area = np.max(stats_without_back, axis=0)[-1]
  #獲取面積最大聯(lián)通組件的index
  max_area_index = stats_without_back[:, -1]==max_area
  rect = stats_without_back[max_area_index]
  return np.squeeze(rect)[0:4]

def get_roi_Kmeans(image_path):
  image = cv2.imread(image_path, cv2.IMREAD_COLOR)
  image_data = image.reshape(-1, 3).astype(np.float32) #必須要轉成浮點類型進行計算
  #簇內(nèi)平方和，標簽和每個簇的中心
  criteria = (cv2.TERM_CRITERIA_EPS + cv2.TERM_CRITERIA_COUNT, 10, 1)
  interia, label, centers = cv2.kmeans(image_data, 2, None, criteria, 5, cv2.KMEANS_RANDOM_CENTERS)
  #二值化，將標簽為0的轉換為255，即是目標
  label[label==0] = 255
  label[label==1] = 0
  #轉換數(shù)據(jù)類型，輪廓查找要是uint8類型數(shù)據(jù)
  thresh_img = label.reshape(image.shape[0:2]).astype(np.uint8)
  x_grad = cv2.Sobel(thresh_img, cv2.CV_32F, 1, 0)
  y_grad = cv2.Sobel(thresh_img, cv2.CV_32F, 0, 1)

  x_grad = cv2.convertScaleAbs(x_grad) #ax + b 線性變換
  y_grad = cv2.convertScaleAbs(y_grad)
  
  dst = cv2.add(x_grad, y_grad, dtype=cv2.CV_16S) #將兩種sobel的加起來就可以得到整個邊緣
  dst = cv2.convertScaleAbs(dst)
  plt.imshow(dst, cmap='gray')
  #輪廓查找目標必須為1
  contours, hierarchy = cv2.findContours(dst, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
  #獲取外接矩形
  rect = cv2.boundingRect(contours[0])
  return rect