Contour Single blob with multiple object [closed]

asked 2018-09-24 01:40:43 -0600

balasubramaniyan94 gravatar image

Hi to everyone.

I'm developing an object shape identification application and struck up with separating close objects using contour, Since close objects are identified as single contour. Is there way to separate the objects?

Things I have tried: 1. I have tried Image segmentation with distance transform and Watershed algorithm - It works for few images only 2. I have tried to separate the objects manual using the distance between two points as mentioned in http://answers.opencv.org/question/71... - I struck up with choosing the points that will separate the object.

I have attached a sample contour for the reference.

image description

Please suggest any comments to separate the objects.

edit retag flag offensive reopen merge delete

Closed for the following reason question is not relevant or outdated by sturkmen
close date 2020-12-09 04:11:58.349681

Comments

1

Is this your original image? If not, maybe try separate objects before getting contour. Also, it will be helpful to see the original image.

yancey gravatar imageyancey ( 2018-09-24 14:13:32 -0600 )edit

Hi yancey, This is not the original image. How to separate the object before contour?. Please suggest.

balasubramaniyan94 gravatar imagebalasubramaniyan94 ( 2018-09-25 01:07:20 -0600 )edit

@balasubramaniyan94 how did you generate this image from your original image?

yancey gravatar imageyancey ( 2018-09-25 09:18:15 -0600 )edit

Initially we will apply GaussianBlur to the original image and then we will apply binary thresholding and finally use findcontour function find the contour points.

balasubramaniyan94 gravatar imagebalasubramaniyan94 ( 2018-09-25 10:06:44 -0600 )edit

@balasubramaniyan94, when you do binary thresholding, is it possible to separate these objects there?

yancey gravatar imageyancey ( 2018-09-25 13:16:31 -0600 )edit

@yancey We are unable to separate the object during thresholding. Please suggest methods, if any.

balasubramaniyan94 gravatar imagebalasubramaniyan94 ( 2018-10-01 05:18:26 -0600 )edit

show the original image and we may give you some help

jsxyhelu gravatar imagejsxyhelu ( 2018-10-06 08:45:00 -0600 )edit
add a comment