I have extracted DenseSIFT from the query and database image and quantized by
kmeans. The challenge is to find those SIFT features that quantized to the same visual words and be spatially consistent (have a similar position to object centers). I have tried few techniques:
- using FLANN() on the SIFT (normal SIFT) coordinates on both query and database image and find the nearest neighbor and then comparing the visual words (NOTE: this gave few points that did not work).
- Using Coherent-Point-Drift (CPD) on SIFT coordinates to find the matched points (I am not sure about this whether it is a right solution or not).
I am struggling with it for many days, and I hope experts can guide me with this. What are the possible solutions or algorithms that I can use for solving this?