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
Pengambilan semula imej kompleks berasaskan kandungan yang cekap adalah tugas yang mencabar kerana objek yang dikesan mungkin muncul dalam pelbagai skala, putaran dan orientasi dengan pelbagai jenis warna dan bentuk latar belakang. Dalam makalah ini, kami mencadangkan perwakilan baru objek dengan pelbagai warna, graf kejiranan-bersebelahan ruang (SNAG), yang boleh berfungsi sebagai asas untuk mengesan objek mengikut kandungan warna daripada imej calon. SNAG terdiri daripada satu set bucu utama dan dua set tepi. Setiap bucu utama mewakili kawasan warna tunggal objek berbilang warna, dan tepi dibahagikan kepada dua kelas: Tepi kejiranan mewakili hubungan kejiranan antara dua bucu utama dengan warna yang sama, dan tepi bersebelahan mewakili hubungan bersebelahan antara bucu utama dan satu lagi. puncak dengan warna yang berbeza. Dengan menyiasat sama ada SNAG imej objek ialah subgraf isomorfik SNAG bagi imej calon, kita boleh menentukan sama ada objek serupa wujud dalam imej calon. Di samping itu, kami juga telah menggunakan pendekatan yang dicadangkan untuk pelbagai masalah pengesanan objek berbeza yang melibatkan latar belakang yang kompleks, dan keberkesanan telah dibuktikan.
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.
Salinan
Yuehu LIU, Shinji OZAWA, "A New Representation and Detection of Multi-Colored Object Based on Color Contents" in IEICE TRANSACTIONS on Information,
vol. E83-D, no. 5, pp. 1160-1169, May 2000, doi: .
Abstract: Efficient content-based retrieval of complex images is a challenging task since the detected object may appear in various scale, rotation and orientation with a wide variety of background colors and forms. In this paper, we propose a novel representation of objects with multiple colors, the spatial neighborhood-adjacency graph(SNAG), which can serve as a basis for detecting object by color contents from the candidate image. The SNAG consists of a set of main-vertices and two sets of edges. Each main-vertex represents a single color region of multi-colored object, and edges are divided into two classes: Neighborhood edges representing neighborhood relationship between two main-vertices with similar color, and adjacency edges representing adjacency relationship between a main-vertex and another vertex with different color. By investigating whether SNAG of object image is an isomorphic subgraph of SNAG of a candidate image, we can determine whether the similar object exists in the candidate image. In addition, we have also applied the proposed approach to a range of different object detection problems involving complex background, and effectiveness has been proved.
URL: https://global.ieice.org/en_transactions/information/10.1587/e83-d_5_1160/_p
Salinan
@ARTICLE{e83-d_5_1160,
author={Yuehu LIU, Shinji OZAWA, },
journal={IEICE TRANSACTIONS on Information},
title={A New Representation and Detection of Multi-Colored Object Based on Color Contents},
year={2000},
volume={E83-D},
number={5},
pages={1160-1169},
abstract={Efficient content-based retrieval of complex images is a challenging task since the detected object may appear in various scale, rotation and orientation with a wide variety of background colors and forms. In this paper, we propose a novel representation of objects with multiple colors, the spatial neighborhood-adjacency graph(SNAG), which can serve as a basis for detecting object by color contents from the candidate image. The SNAG consists of a set of main-vertices and two sets of edges. Each main-vertex represents a single color region of multi-colored object, and edges are divided into two classes: Neighborhood edges representing neighborhood relationship between two main-vertices with similar color, and adjacency edges representing adjacency relationship between a main-vertex and another vertex with different color. By investigating whether SNAG of object image is an isomorphic subgraph of SNAG of a candidate image, we can determine whether the similar object exists in the candidate image. In addition, we have also applied the proposed approach to a range of different object detection problems involving complex background, and effectiveness has been proved.},
keywords={},
doi={},
ISSN={},
month={May},}
Salinan
TY - JOUR
TI - A New Representation and Detection of Multi-Colored Object Based on Color Contents
T2 - IEICE TRANSACTIONS on Information
SP - 1160
EP - 1169
AU - Yuehu LIU
AU - Shinji OZAWA
PY - 2000
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E83-D
IS - 5
JA - IEICE TRANSACTIONS on Information
Y1 - May 2000
AB - Efficient content-based retrieval of complex images is a challenging task since the detected object may appear in various scale, rotation and orientation with a wide variety of background colors and forms. In this paper, we propose a novel representation of objects with multiple colors, the spatial neighborhood-adjacency graph(SNAG), which can serve as a basis for detecting object by color contents from the candidate image. The SNAG consists of a set of main-vertices and two sets of edges. Each main-vertex represents a single color region of multi-colored object, and edges are divided into two classes: Neighborhood edges representing neighborhood relationship between two main-vertices with similar color, and adjacency edges representing adjacency relationship between a main-vertex and another vertex with different color. By investigating whether SNAG of object image is an isomorphic subgraph of SNAG of a candidate image, we can determine whether the similar object exists in the candidate image. In addition, we have also applied the proposed approach to a range of different object detection problems involving complex background, and effectiveness has been proved.
ER -