The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
동일한 물체나 장면의 두 이미지 사이의 대응 관계를 찾는 것은 컴퓨터 비전의 활발한 연구 분야입니다. 본 논문에서는 다중 기능 융합 기술을 통해 슈퍼픽셀의 콘텐츠를 활용하는 빠르고 효과적인 CSIS(Content-based Superpixel Image Matching and Stitching) 방식을 개발합니다. 널리 사용되는 키포인트 기반 매칭 방법과 달리 우리의 접근 방식은 이미지 매칭을 구현하기 위해 슈퍼픽셀 내부 특징 기반 방식을 제안합니다. 처음에는 콘텐츠 기반 슈퍼픽셀 분할(CSS) 알고리즘이라는 콘텐츠 기반 특징 표현을 기반으로 하는 새로운 슈퍼픽셀 생성 알고리즘을 사용합니다. 슈퍼픽셀은 색상, 공간 및 그라데이션 특징 정보를 사용하여 새로운 거리 측정 기준으로 생성됩니다. 이는 결과 슈퍼픽셀의 컴팩트함과 경계 준수의 균형을 맞추기 위해 개발되었습니다. 그런 다음 중요한 특성을 가진 일부 슈퍼픽셀을 분리하기 위해 각 슈퍼픽셀의 엔트로피를 계산합니다. 다음으로, 선택된 각 슈퍼픽셀에 대해 선택된 슈퍼픽셀 자체의 로컬 특징을 추출하고 융합하여 다중 기능 설명자가 생성됩니다. 마지막으로 후보 슈퍼픽셀과 그 주변의 일치 특징을 비교하여 두 이미지 간의 일치성을 추정합니다. 우리는 슈퍼픽셀 영역 설명자를 사용하여 복잡하고 변형 가능한 표면에서 슈퍼픽셀 매칭과 이미지 스티칭을 평가했으며, 결과는 새로운 방법이 정확도와 실행 속도를 매칭하는 데 효과적이라는 것을 보여줍니다.
Jianmei ZHANG
East China University of Science and Technology
Pengyu WANG
East China University of Science and Technology
Feiyang GONG
East China University of Science and Technology
Hongqing ZHU
East China University of Science and Technology
Ning CHEN
East China University of Science and Technology
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.
부
Jianmei ZHANG, Pengyu WANG, Feiyang GONG, Hongqing ZHU, Ning CHEN, "Content-Based Superpixel Segmentation and Matching Using Its Region Feature Descriptors" in IEICE TRANSACTIONS on Information,
vol. E103-D, no. 8, pp. 1888-1900, August 2020, doi: 10.1587/transinf.2019EDP7322.
Abstract: Finding the correspondence between two images of the same object or scene is an active research field in computer vision. This paper develops a rapid and effective Content-based Superpixel Image matching and Stitching (CSIS) scheme, which utilizes the content of superpixel through multi-features fusion technique. Unlike popular keypoint-based matching method, our approach proposes a superpixel internal feature-based scheme to implement image matching. In the beginning, we make use of a novel superpixel generation algorithm based on content-based feature representation, named Content-based Superpixel Segmentation (CSS) algorithm. Superpixels are generated in terms of a new distance metric using color, spatial, and gradient feature information. It is developed to balance the compactness and the boundary adherence of resulted superpixels. Then, we calculate the entropy of each superpixel for separating some superpixels with significant characteristics. Next, for each selected superpixel, its multi-features descriptor is generated by extracting and fusing local features of the selected superpixel itself. Finally, we compare the matching features of candidate superpixels and their own neighborhoods to estimate the correspondence between two images. We evaluated superpixel matching and image stitching on complex and deformable surfaces using our superpixel region descriptors, and the results show that new method is effective in matching accuracy and execution speed.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2019EDP7322/_p
부
@ARTICLE{e103-d_8_1888,
author={Jianmei ZHANG, Pengyu WANG, Feiyang GONG, Hongqing ZHU, Ning CHEN, },
journal={IEICE TRANSACTIONS on Information},
title={Content-Based Superpixel Segmentation and Matching Using Its Region Feature Descriptors},
year={2020},
volume={E103-D},
number={8},
pages={1888-1900},
abstract={Finding the correspondence between two images of the same object or scene is an active research field in computer vision. This paper develops a rapid and effective Content-based Superpixel Image matching and Stitching (CSIS) scheme, which utilizes the content of superpixel through multi-features fusion technique. Unlike popular keypoint-based matching method, our approach proposes a superpixel internal feature-based scheme to implement image matching. In the beginning, we make use of a novel superpixel generation algorithm based on content-based feature representation, named Content-based Superpixel Segmentation (CSS) algorithm. Superpixels are generated in terms of a new distance metric using color, spatial, and gradient feature information. It is developed to balance the compactness and the boundary adherence of resulted superpixels. Then, we calculate the entropy of each superpixel for separating some superpixels with significant characteristics. Next, for each selected superpixel, its multi-features descriptor is generated by extracting and fusing local features of the selected superpixel itself. Finally, we compare the matching features of candidate superpixels and their own neighborhoods to estimate the correspondence between two images. We evaluated superpixel matching and image stitching on complex and deformable surfaces using our superpixel region descriptors, and the results show that new method is effective in matching accuracy and execution speed.},
keywords={},
doi={10.1587/transinf.2019EDP7322},
ISSN={1745-1361},
month={August},}
부
TY - JOUR
TI - Content-Based Superpixel Segmentation and Matching Using Its Region Feature Descriptors
T2 - IEICE TRANSACTIONS on Information
SP - 1888
EP - 1900
AU - Jianmei ZHANG
AU - Pengyu WANG
AU - Feiyang GONG
AU - Hongqing ZHU
AU - Ning CHEN
PY - 2020
DO - 10.1587/transinf.2019EDP7322
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E103-D
IS - 8
JA - IEICE TRANSACTIONS on Information
Y1 - August 2020
AB - Finding the correspondence between two images of the same object or scene is an active research field in computer vision. This paper develops a rapid and effective Content-based Superpixel Image matching and Stitching (CSIS) scheme, which utilizes the content of superpixel through multi-features fusion technique. Unlike popular keypoint-based matching method, our approach proposes a superpixel internal feature-based scheme to implement image matching. In the beginning, we make use of a novel superpixel generation algorithm based on content-based feature representation, named Content-based Superpixel Segmentation (CSS) algorithm. Superpixels are generated in terms of a new distance metric using color, spatial, and gradient feature information. It is developed to balance the compactness and the boundary adherence of resulted superpixels. Then, we calculate the entropy of each superpixel for separating some superpixels with significant characteristics. Next, for each selected superpixel, its multi-features descriptor is generated by extracting and fusing local features of the selected superpixel itself. Finally, we compare the matching features of candidate superpixels and their own neighborhoods to estimate the correspondence between two images. We evaluated superpixel matching and image stitching on complex and deformable surfaces using our superpixel region descriptors, and the results show that new method is effective in matching accuracy and execution speed.
ER -