Memory Saving Feature Descriptor Using Scale and Rotation Invariant Patches around the Feature Ppoints

Masamichi KITAGAWA  Ikuko SHIMIZU  

IEICE TRANSACTIONS on Information and Systems   Vol.E102-D   No.5   pp.1106-1110
Publication Date: 2019/05/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2018EDL8176
Type of Manuscript: LETTER
Category: Image Recognition, Computer Vision
image matching,  feature descriptor,  keypoints,  

Full Text: FreePDF(707KB)

To expand the use of systems using a camera on portable devices such as tablets and smartphones, we have developed and propose a memory saving feature descriptor, the use of which is one of the essential techniques in computer vision. The proposed descriptor compares pixel values of pre-fixed positions in the small patch around the feature point and stores binary values. Like the conventional descriptors, it extracts the patch on the basis of the scale and orientation of the feature point. For memories of the same size, it achieves higher accuracy than ORB and BRISK in all cases and AKAZE for the images with textured regions.