Farmland Image w/ anomaly:
In the picture above, the blue outline outlines the anomalous part of the farmland, where the plants are much more dense also known as "Double Planting".
I'm looking for ideas, approaches, or algorithms I can try, to see if it is able to properly cluster the anomalous parts of the farmland seperately from the rest of the land.
This has been my approach so far howerver it is not able to cluster the image properly and identify the anomalous part of the image.
I divide the image into a set of cells (e.g., 16x16), and cluster the cells using hierarchical clustering with one constraint.
A cluster C1 can be merged with another cluster C2 to make a bigger cluster only if C1 contains a cell c1 and C2 contains a cell c2, and c1 and c2 are neighbours. (capital C indicates cluster while lowercase c indicates cell)
Intially, each cell starts out in its own cluster.
Distance between two clusters C1 and C2 is defined as either the Euclidean or Bhattacharyaa distance between the histogram over all pixels that are inside C1 and the histogram of all pixels inside C2
