官术网_书友最值得收藏!

Thresholding

After removing the background, we only have to binarize the image for future segmentation. We are going to do this with threshold. Threshold is a simple function that sets each pixel's values to a maximum value (255, for example). If the pixel's value is greater than the threshold value or if the pixel's value is lower than the threshold value, it will be set to a minimum (0):

Now, we are going to apply the threshold function using two different threshold values: we will use a 30 threshold value when we remove the light/background because all non-interesting regions are black. This is because we apply background removal. We will also a medium value threshold (140) when we do not use a light removal method, because we have a white background. This last option is used to allow us to check the results with and without background removal:

  // Binarize image for segment 
  Mat img_thr; 
  if(method_light!=2){ 
   threshold(img_no_light, img_thr, 30, 255, THRESH_BINARY); 
  }else{ 
   threshold(img_no_light, img_thr, 140, 255, THRESH_BINARY_INV); 
  } 

Now, we are going to continue with the most important part of our application: the segmentation. We are going to use two different approaches or algorithms here: connected components and find contours.

主站蜘蛛池模板: 广丰县| 土默特左旗| 安塞县| 荣昌县| 日土县| 拉萨市| 安多县| 华亭县| 南雄市| 蓝山县| 黎城县| 汉阴县| 武宣县| 武清区| 江华| 惠水县| 建阳市| 赤城县| 岳池县| 绍兴县| 泾阳县| 磐安县| 菏泽市| 揭西县| 贵南县| 林甸县| 左云县| 成武县| 大关县| 呼图壁县| 冷水江市| 额敏县| 涿鹿县| 梨树县| 衡东县| 普格县| 永德县| 仪征市| 金华市| 南陵县| 呼和浩特市|