AIGIF: Adaptively Integrated Gradient and Intensity Feature for Robust and Low-Dimensional Description of Local Keypoint

Songlin DU  Takeshi IKENAGA  

IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences   Vol.E100-A    No.11    pp.2275-2284
Publication Date: 2017/11/01
Online ISSN: 1745-1337
DOI: 10.1587/transfun.E100.A.2275
Type of Manuscript: Special Section PAPER (Special Section on Smart Multimedia & Communication Systems)
Category: Vision
local keypoint descriptor,  gradient magnitude,  gradient orientation,  intensity comparison,  image matching,  

Full Text: PDF(3.6MB)>>
Buy this Article

Establishing local visual correspondences between images taken under different conditions is an important and challenging task in computer vision. A common solution for this task is detecting keypoints in images and then matching the keypoints with a feature descriptor. This paper proposes a robust and low-dimensional local feature descriptor named Adaptively Integrated Gradient and Intensity Feature (AIGIF). The proposed AIGIF descriptor partitions the support region surrounding each keypoint into sub-regions, and classifies the sub-regions into two categories: edge-dominated ones and smoothness-dominated ones. For edge-dominated sub-regions, gradient magnitude and orientation features are extracted; for smoothness-dominated sub-regions, intensity feature is extracted. The gradient and intensity features are integrated to generate the descriptor. Experiments on image matching were conducted to evaluate performances of the proposed AIGIF. Compared with SIFT, the proposed AIGIF achieves 75% reduction of feature dimension (from 128 bytes to 32 bytes); compared with SURF, the proposed AIGIF achieves 87.5% reduction of feature dimension (from 256 bytes to 32 bytes); compared with the state-of-the-art ORB descriptor which has the same feature dimension with AIGIF, AIGIF achieves higher accuracy and robustness. In summary, the AIGIF combines the advantages of gradient feature and intensity feature, and achieves relatively high accuracy and robustness with low feature dimension.