| アイテムタイプ |
学術雑誌論文 = Journal Article(1) |
| 公開日 |
2024-05-13 |
| 資源タイプ |
|
|
資源タイプ識別子 |
http://purl.org/coar/resource_type/c_6501 |
|
資源タイプ |
journal article |
| タイトル |
|
|
タイトル |
A Comparative Study of Vector and Raster Spatial Data for Image Segmentation Focusing on the Position Estimation Accuracy of Vertices to Form Polygonal Shapes |
|
言語 |
en |
| その他のタイトル |
|
|
その他のタイトル |
A COMPARATIVE STUDY OF VECTOR AND RASTER SPATIAL DATA FOR IMAGE SEGMENTATION FOCUSING ON THE POSITION ESTIMATION ACCURACY OF VERTICES TO FORM POLYGONAL SHAPES |
|
言語 |
en |
| 言語 |
|
|
言語 |
eng |
| 著者 |
Altaweel, Ahmad
Almassri, Ahmad
Purev, Amarbold
我妻, 広明
|
| 抄録 |
|
|
内容記述タイプ |
Abstract |
|
内容記述 |
In the field of image processing, raster data is frequently used for image segmentation and shape estimations for general purposes. On the other hand, in the medical field, which aims to help doctors in surgical operations, semi-automatic robotic manipulations such as the da Vinci Surgical Systemto minimize the necessary area to open for the living body. In the present study, a computational geometry-based method was proposed for vector data to treat the rearrangement of extracted points as candidates for edges of the target shape. On the other hand, the Harris-Stephens algorithm was introduced as a well-known method to detect vertices to form polygonal shapes in raster data as the counterpart in the comparative study. Typically, such a raster data method is not robust to perform in noisy conditions without appropriate filtering in the pre-processing. In the Harris-Stephens algorithm, the adding noises were detected as new vertices to form shapes in the area, which is inevitable in the condition without any semantic information about the shape. Since the proposed computational geometry-based method contains geometrical properties in its computation, it can be enhanced to be robust against noisy data. In the sense of designing a part of the system to be a surgical robot, which requires high accuracy of the position estimation of the target, a maximization of extractions of geometrical properties provides a significant benefit for accurate manipulation of robotic arms. It contributes not only to surgical robots but also to the solver of 2D replacement puzzles known as tangram puzzles to be a general scheme for robots in all fields behaving in dynamic environments. |
|
言語 |
en |
| 書誌情報 |
en : International Journal of Engineering Advanced Research
巻 4,
号 3,
p. 25-34,
発行日 2022-09-07
|
| 出版社 |
|
|
出版者 |
Academia Industry Networks |
|
言語 |
en |
| URI |
|
|
|
識別子タイプ |
URI |
|
|
関連識別子 |
https://myjms.mohe.gov.my/index.php/ijear/article/view/19533 |
| ISSN |
|
|
収録物識別子タイプ |
EISSN |
|
収録物識別子 |
2710-7167 |
| 著作権関連情報 |
|
|
権利情報 |
Copyright (c) 2022 ACADEMIA INDUSTRY NETWORKS. All rights reserved. |
| 出版タイプ |
|
|
出版タイプ |
VoR |
|
出版タイプResource |
http://purl.org/coar/version/c_970fb48d4fbd8a85 |
| 査読の有無 |
|
|
値 |
yes |
| 研究者情報 |
|
|
URL |
https://hyokadb02.jimu.kyutech.ac.jp/html/358_ja.html |
| 論文ID（連携） |
|
|
値 |
10430470 |
| 連携ID |
|
|
値 |
12241 |
10430470.pdf (459 KB)
