Revision history [back]

if you skip images in training, you'll have to skip them for the detection later, too.

inserting an empty feature vector here, like:

        if len(kp) < 1:
            b_o_w.add(np.zeros(1, sift.descriptorSize()), np.float32)

most likely, you'll have an additional, "NOT-FOUND" cluster in your BOW.

try and tell us the outcome !

if you skip images in training, you'll have to skip them for the detection later, too.

inserting an empty feature vector here, like:

        if len(kp) < 1:
            b_o_w.add(np.zeros(1, no_kp = np.zeros((1, sift.descriptorSize()), np.float32)
            b_o_w.add(no_kp)

most likely, you'll have an additional, "NOT-FOUND" cluster in your BOW.

try and tell us the outcome !