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
A correspondência convencional baseada em pontos de interesse requer um pré-processamento de patch computacionalmente caro e não é apropriada para o reconhecimento de objetos simples com detalhes insignificantes. Este artigo apresenta um método para extrair regiões de interesse distintas de imagens que podem ser usadas para realizar correspondência confiável entre diferentes visualizações de objetos ou cenas simples. Formulamos o problema de correspondência em uma estrutura de classificação Naive Bayesiana e uma correspondência simples baseada em correlação, o que torna nosso sistema rápido, simples, eficiente e robusto. Para facilitar o casamento utilizando um número muito pequeno de regiões de interesse, propomos também um método para reduzir a área de busca dentro de uma cena de teste. Usando este método, é possível identificar objetos de forma robusta entre desordem e oclusão, ao mesmo tempo em que obtém desempenho quase em tempo real. Nosso sistema funciona notavelmente bem em objetos simples onde alguns métodos de última geração falham. Como nosso sistema é particularmente adequado para o reconhecimento de objetos simples, nos referimos a ele como Simple Plane Object Recognizer (SPOR).
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.
Copiar
Al MANSUR, Katsutoshi SAKATA, Dipankar DAS, Yoshinori KUNO, "Recognition of Plain Objects Using Local Region Matching" in IEICE TRANSACTIONS on Information,
vol. E91-D, no. 7, pp. 1906-1913, July 2008, doi: 10.1093/ietisy/e91-d.7.1906.
Abstract: Conventional interest point based matching requires computationally expensive patch preprocessing and is not appropriate for recognition of plain objects with negligible detail. This paper presents a method for extracting distinctive interest regions from images that can be used to perform reliable matching between different views of plain objects or scene. We formulate the correspondence problem in a Naive Bayesian classification framework and a simple correlation based matching, which makes our system fast, simple, efficient, and robust. To facilitate the matching using a very small number of interest regions, we also propose a method to reduce the search area inside a test scene. Using this method, it is possible to robustly identify objects among clutter and occlusion while achieving near real-time performance. Our system performs remarkably well on plain objects where some state-of-the art methods fail. Since our system is particularly suitable for the recognition of plain object, we refer to it as Simple Plane Object Recognizer (SPOR).
URL: https://global.ieice.org/en_transactions/information/10.1093/ietisy/e91-d.7.1906/_p
Copiar
@ARTICLE{e91-d_7_1906,
author={Al MANSUR, Katsutoshi SAKATA, Dipankar DAS, Yoshinori KUNO, },
journal={IEICE TRANSACTIONS on Information},
title={Recognition of Plain Objects Using Local Region Matching},
year={2008},
volume={E91-D},
number={7},
pages={1906-1913},
abstract={Conventional interest point based matching requires computationally expensive patch preprocessing and is not appropriate for recognition of plain objects with negligible detail. This paper presents a method for extracting distinctive interest regions from images that can be used to perform reliable matching between different views of plain objects or scene. We formulate the correspondence problem in a Naive Bayesian classification framework and a simple correlation based matching, which makes our system fast, simple, efficient, and robust. To facilitate the matching using a very small number of interest regions, we also propose a method to reduce the search area inside a test scene. Using this method, it is possible to robustly identify objects among clutter and occlusion while achieving near real-time performance. Our system performs remarkably well on plain objects where some state-of-the art methods fail. Since our system is particularly suitable for the recognition of plain object, we refer to it as Simple Plane Object Recognizer (SPOR).},
keywords={},
doi={10.1093/ietisy/e91-d.7.1906},
ISSN={1745-1361},
month={July},}
Copiar
TY - JOUR
TI - Recognition of Plain Objects Using Local Region Matching
T2 - IEICE TRANSACTIONS on Information
SP - 1906
EP - 1913
AU - Al MANSUR
AU - Katsutoshi SAKATA
AU - Dipankar DAS
AU - Yoshinori KUNO
PY - 2008
DO - 10.1093/ietisy/e91-d.7.1906
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E91-D
IS - 7
JA - IEICE TRANSACTIONS on Information
Y1 - July 2008
AB - Conventional interest point based matching requires computationally expensive patch preprocessing and is not appropriate for recognition of plain objects with negligible detail. This paper presents a method for extracting distinctive interest regions from images that can be used to perform reliable matching between different views of plain objects or scene. We formulate the correspondence problem in a Naive Bayesian classification framework and a simple correlation based matching, which makes our system fast, simple, efficient, and robust. To facilitate the matching using a very small number of interest regions, we also propose a method to reduce the search area inside a test scene. Using this method, it is possible to robustly identify objects among clutter and occlusion while achieving near real-time performance. Our system performs remarkably well on plain objects where some state-of-the art methods fail. Since our system is particularly suitable for the recognition of plain object, we refer to it as Simple Plane Object Recognizer (SPOR).
ER -