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
Padanan bentuk dengan deskriptor tempatan ialah skema asas dalam analisis bentuk. Kami boleh mengesahkan secara visual hasil padanan dan juga menilai mereka untuk klasifikasi bentuk. Secara amnya, padanan bentuk dilaksanakan dengan menentukan kesesuaian antara bentuk yang diwakili oleh set titik sampel masing-masing. Beberapa kaedah pemadanan telah pun dicadangkan; perbezaan utama antara mereka terletak pada pilihan fungsi kos padanan mereka. Fungsi ini mengukur perbezaan antara taburan setempat titik sampel di sekitar titik fokus satu bentuk dan taburan setempat titik sampel di sekitar titik rujukan bentuk lain. Deskriptor tempatan digunakan untuk menerangkan taburan titik sampel di sekeliling titik bentuk. Dalam makalah ini, kami mencadangkan skema lanjutan untuk pemadanan bentuk yang boleh mengimbangi ralat dalam deskriptor tempatan sedia ada. Adalah mudah bagi deskriptor tempatan untuk mengguna pakai skema kami kerana ia tidak memerlukan deskriptor tempatan untuk diubah suai. Idea utama skema kami adalah untuk mempertimbangkan korespondensi titik sampel yang berdekatan dengan titik fokus apabila menentukan korespondensi titik fokus. Ini berguna kerana ia meningkatkan peluang untuk mencari surat-menyurat yang sesuai. Walau bagaimanapun, mempertimbangkan korespondensi titik jiran menyebabkan masalah mengenai kebolehlaksanaan pengiraan, kerana terdapat peningkatan yang ketara dalam bilangan kemungkinan surat-menyurat yang perlu dipertimbangkan dalam pemadanan bentuk. Kami menyelesaikan masalah ini menggunakan algoritma cawangan dan terikat, untuk penghampiran yang cekap. Menggunakan beberapa set data bentuk, kami menunjukkan bahawa skema kami menghasilkan padanan yang lebih sesuai daripada skema konvensional yang tidak mempertimbangkan korespondensi titik sampel yang berdekatan, walaupun skema kami hanya memerlukan sedikit peningkatan dalam masa pelaksanaan.
Kazunori IWATA
Hiroshima City University
Hiroki YAMAMOTO
Hiroshima City University
Kazushi MIMURA
Hiroshima City 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.
Salinan
Kazunori IWATA, Hiroki YAMAMOTO, Kazushi MIMURA, "An Extended Scheme for Shape Matching with Local Descriptors" in IEICE TRANSACTIONS on Information,
vol. E104-D, no. 2, pp. 285-293, February 2021, doi: 10.1587/transinf.2020EDP7134.
Abstract: Shape matching with local descriptors is an underlying scheme in shape analysis. We can visually confirm the matching results and also assess them for shape classification. Generally, shape matching is implemented by determining the correspondence between shapes that are represented by their respective sets of sampled points. Some matching methods have already been proposed; the main difference between them lies in their choice of matching cost function. This function measures the dissimilarity between the local distribution of sampled points around a focusing point of one shape and the local distribution of sampled points around a referring point of another shape. A local descriptor is used to describe the distribution of sampled points around the point of the shape. In this paper, we propose an extended scheme for shape matching that can compensate for errors in existing local descriptors. It is convenient for local descriptors to adopt our scheme because it does not require the local descriptors to be modified. The main idea of our scheme is to consider the correspondence of neighboring sampled points to a focusing point when determining the correspondence of the focusing point. This is useful because it increases the chance of finding a suitable correspondence. However, considering the correspondence of neighboring points causes a problem regarding computational feasibility, because there is a substantial increase in the number of possible correspondences that need to be considered in shape matching. We solve this problem using a branch-and-bound algorithm, for efficient approximation. Using several shape datasets, we demonstrate that our scheme yields a more suitable matching than the conventional scheme that does not consider the correspondence of neighboring sampled points, even though our scheme requires only a small increase in execution time.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2020EDP7134/_p
Salinan
@ARTICLE{e104-d_2_285,
author={Kazunori IWATA, Hiroki YAMAMOTO, Kazushi MIMURA, },
journal={IEICE TRANSACTIONS on Information},
title={An Extended Scheme for Shape Matching with Local Descriptors},
year={2021},
volume={E104-D},
number={2},
pages={285-293},
abstract={Shape matching with local descriptors is an underlying scheme in shape analysis. We can visually confirm the matching results and also assess them for shape classification. Generally, shape matching is implemented by determining the correspondence between shapes that are represented by their respective sets of sampled points. Some matching methods have already been proposed; the main difference between them lies in their choice of matching cost function. This function measures the dissimilarity between the local distribution of sampled points around a focusing point of one shape and the local distribution of sampled points around a referring point of another shape. A local descriptor is used to describe the distribution of sampled points around the point of the shape. In this paper, we propose an extended scheme for shape matching that can compensate for errors in existing local descriptors. It is convenient for local descriptors to adopt our scheme because it does not require the local descriptors to be modified. The main idea of our scheme is to consider the correspondence of neighboring sampled points to a focusing point when determining the correspondence of the focusing point. This is useful because it increases the chance of finding a suitable correspondence. However, considering the correspondence of neighboring points causes a problem regarding computational feasibility, because there is a substantial increase in the number of possible correspondences that need to be considered in shape matching. We solve this problem using a branch-and-bound algorithm, for efficient approximation. Using several shape datasets, we demonstrate that our scheme yields a more suitable matching than the conventional scheme that does not consider the correspondence of neighboring sampled points, even though our scheme requires only a small increase in execution time.},
keywords={},
doi={10.1587/transinf.2020EDP7134},
ISSN={1745-1361},
month={February},}
Salinan
TY - JOUR
TI - An Extended Scheme for Shape Matching with Local Descriptors
T2 - IEICE TRANSACTIONS on Information
SP - 285
EP - 293
AU - Kazunori IWATA
AU - Hiroki YAMAMOTO
AU - Kazushi MIMURA
PY - 2021
DO - 10.1587/transinf.2020EDP7134
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E104-D
IS - 2
JA - IEICE TRANSACTIONS on Information
Y1 - February 2021
AB - Shape matching with local descriptors is an underlying scheme in shape analysis. We can visually confirm the matching results and also assess them for shape classification. Generally, shape matching is implemented by determining the correspondence between shapes that are represented by their respective sets of sampled points. Some matching methods have already been proposed; the main difference between them lies in their choice of matching cost function. This function measures the dissimilarity between the local distribution of sampled points around a focusing point of one shape and the local distribution of sampled points around a referring point of another shape. A local descriptor is used to describe the distribution of sampled points around the point of the shape. In this paper, we propose an extended scheme for shape matching that can compensate for errors in existing local descriptors. It is convenient for local descriptors to adopt our scheme because it does not require the local descriptors to be modified. The main idea of our scheme is to consider the correspondence of neighboring sampled points to a focusing point when determining the correspondence of the focusing point. This is useful because it increases the chance of finding a suitable correspondence. However, considering the correspondence of neighboring points causes a problem regarding computational feasibility, because there is a substantial increase in the number of possible correspondences that need to be considered in shape matching. We solve this problem using a branch-and-bound algorithm, for efficient approximation. Using several shape datasets, we demonstrate that our scheme yields a more suitable matching than the conventional scheme that does not consider the correspondence of neighboring sampled points, even though our scheme requires only a small increase in execution time.
ER -