Ask Your Question

Revision history [back]

How to get SIFT features as floating point?

When I run sift.compute (or sift.detectAndCompute), in python3 (via anaconda), the descriptors come as np.uint8 arrays.

In the OpenCV source code, the descriptor is returned as floating point, so I am wondering how do I get the descriptors in python as floating point numbers?

How to get SIFT features as floating point?

When I run sift.compute (or sift.detectAndCompute), in python3 (via anaconda), the descriptors come as np.uint8 arrays.get truncated to integer arrays instead of floating point.

In the OpenCV source code, the descriptor is returned as floating point, so I am wondering how do I get the descriptors in python as the original floating point numbers? numbers?