AIGIF: Adaptively integrated gradient and intensity feature for robust and low-dimensional description of local keypoint

Songlin Du, Takeshi Ikenaga

研究成果: Article

2 引用 (Scopus)

抄録

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 edgedominated 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.

元の言語English
ページ(範囲)2275-2284
ページ数10
ジャーナルIEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
E100A
発行部数11
DOI
出版物ステータスPublished - 2017 11 1

Fingerprint

Gradient
Image matching
Computer vision
Descriptors
Experiments
Smoothness
High Accuracy
Robustness
Image Matching
Scale Invariant Feature Transform
Local Features
Computer Vision
Correspondence
Classify
Partition
Evaluate
Experiment

ASJC Scopus subject areas

  • Signal Processing
  • Computer Graphics and Computer-Aided Design
  • Electrical and Electronic Engineering
  • Applied Mathematics

これを引用

@article{45c5c472e668484bae1372611e6d0e04,
title = "AIGIF: Adaptively integrated gradient and intensity feature for robust and low-dimensional description of local keypoint",
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 edgedominated 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 = "Gradient magnitude, Gradient orientation, Image matching, Intensity comparison, Local keypoint descriptor",
author = "Songlin Du and Takeshi Ikenaga",
year = "2017",
month = "11",
day = "1",
doi = "10.1587/transfun.E100.A.2275",
language = "English",
volume = "E100A",
pages = "2275--2284",
journal = "IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences",
issn = "0916-8508",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "11",

}

TY - JOUR

T1 - AIGIF

T2 - Adaptively integrated gradient and intensity feature for robust and low-dimensional description of local keypoint

AU - Du, Songlin

AU - Ikenaga, Takeshi

PY - 2017/11/1

Y1 - 2017/11/1

N2 - 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 edgedominated 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.

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 edgedominated 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.

KW - Gradient magnitude

KW - Gradient orientation

KW - Image matching

KW - Intensity comparison

KW - Local keypoint descriptor

UR - http://www.scopus.com/inward/record.url?scp=85033462365&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85033462365&partnerID=8YFLogxK

U2 - 10.1587/transfun.E100.A.2275

DO - 10.1587/transfun.E100.A.2275

M3 - Article

AN - SCOPUS:85033462365

VL - E100A

SP - 2275

EP - 2284

JO - IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

JF - IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

SN - 0916-8508

IS - 11

ER -