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.
Songlin DU
Waseda University
Takeshi IKENAGA
Waseda University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Songlin DU, Takeshi IKENAGA, "AIGIF: Adaptively Integrated Gradient and Intensity Feature for Robust and Low-Dimensional Description of Local Keypoint" in IEICE TRANSACTIONS on Fundamentals,
vol. E100-A, no. 11, pp. 2275-2284, November 2017, doi: 10.1587/transfun.E100.A.2275.
Abstract: 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.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.E100.A.2275/_p
Copy
@ARTICLE{e100-a_11_2275,
author={Songlin DU, Takeshi IKENAGA, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={AIGIF: Adaptively Integrated Gradient and Intensity Feature for Robust and Low-Dimensional Description of Local Keypoint},
year={2017},
volume={E100-A},
number={11},
pages={2275-2284},
abstract={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.},
keywords={},
doi={10.1587/transfun.E100.A.2275},
ISSN={1745-1337},
month={November},}
Copy
TY - JOUR
TI - AIGIF: Adaptively Integrated Gradient and Intensity Feature for Robust and Low-Dimensional Description of Local Keypoint
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 2275
EP - 2284
AU - Songlin DU
AU - Takeshi IKENAGA
PY - 2017
DO - 10.1587/transfun.E100.A.2275
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E100-A
IS - 11
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - November 2017
AB - 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.
ER -