I would like to estimate the built-up area by using image edge detection. However, after detecting the edge inside the image, I need to close the area between the edges. Can anyone gudie?
1. Davim, J. P., Rubio, J. C., & Abrao, A. M. (2007). A novel approach based on digital image analysis to evaluate the delamination factor after drilling composite laminates. Composites Science and Technology, 67(9), 1939-1945.
2. Tan, Y. L., Kim, H., Lee, S., Tihan, T., Ver Hoef, L., Mueller, S. G., ... & Knowlton, R. (2018). quantitative surface analysis of combined Mri and Pet enhances detection of focal cortical dysplasias. NeuroImage, 166, 10-18.
3. Li, X., Gao, B., Woo, W. L., Tian, G. Y., Qiu, X., & Gu, L. (2017). Quantitative surface crack evaluation based on eddy current pulsed thermography. IEEE Sensors Journal, 17(2), 412-421.
1. Davim, J. P., Rubio, J. C., & Abrao, A. M. (2007). A novel approach based on digital image analysis to evaluate the delamination factor after drilling composite laminates. Composites Science and Technology, 67(9), 1939-1945.
2. Tan, Y. L., Kim, H., Lee, S., Tihan, T., Ver Hoef, L., Mueller, S. G., ... & Knowlton, R. (2018). quantitative surface analysis of combined Mri and Pet enhances detection of focal cortical dysplasias. NeuroImage, 166, 10-18.
3. Li, X., Gao, B., Woo, W. L., Tian, G. Y., Qiu, X., & Gu, L. (2017). Quantitative surface crack evaluation based on eddy current pulsed thermography. IEEE Sensors Journal, 17(2), 412-421.
For the gaps that are rather small, you could try to perform the following two operations:
1. dilate the mask multiple times (enlarging the thickness of the edge structures)
2. erode the mask (decreasing the thickness of the edge structures again)
This can close small gaps in the edge lines and then you may try to fill the area inside the borders with a Flood Filler, similar to what Mikkel Schou Nielsen mentioned.
The suggestion by Mikkel and Jan work well if the gaps are small. The gaps in the example image are by far too large!
Not only are the gaps too large, but some edges are completely missing and many edges are unwanted because they run across the roof tops, complicating the matter further.
I think there is no way to 'fix' your edges; you need better edges. So it becomes a segmentation problem.
Automatic segmentation of the roof tops can be done for this image (all rectangular buildings, all buildings oriented in the same way, image taken on a sunny day, shadows of buildings are not cast upon other buildings).
If all your images have those characteristics, I can give it some thought, but if the variability of your images is very high, the task is formidable and you might need to resort to artificial intelligence.
But especially for the case of buildings that generally have segments that intersect perpendicular can be tested intersection of two segments perpendicular.
When the distance from the point of cutting to the end of the relevant segment is considered to meet a reasonable distance, then it can be assumed that they are connected.