Reputation: 11
I want to split many images inside one image.
My method :
1- Quantize image using pyramid segmentation.
2- Extract contour from image.
3- Accumulate horizontal & vertical edges.
4- Compute the intersection of the horizontal & vertical lines.
What is your suggestion for this problem?
Please refer to the here to see sample images.
Upvotes: 1
Views: 134
Reputation: 1764
I assume the number and size of the images is variable (if they aren't, then you can easily cut at known distances)
Since the joint between different images is going to generate contrasts, you can use canny plus standard line detection. You can find a good tutorial here . Also check documentation of HoughLines & HoughLinesP.
After detecting the lines, you can discard all the non-horizontal and non-vertical ones. Then, you can find positions and distances between horizontal and vertical lines in order to compute the sub-images boundaries.
Upvotes: 1