WEKO3
アイテム
Matching of CT and X-ray Images using Curvature Scale Space
http://hdl.handle.net/10458/6713
http://hdl.handle.net/10458/671334895725-4db2-49a1-aa79-2c1e38da40a2
| 名前 / ファイル | ライセンス | アクション |
|---|---|---|
本文 (1.7 MB)
|
|
| Item type | 紀要論文 / Departmental Bulletin Paper(1) | |||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 公開日 | 2020-06-21 | |||||||||||||||||
| タイトル | ||||||||||||||||||
| タイトル | Matching of CT and X-ray Images using Curvature Scale Space | |||||||||||||||||
| 言語 | en | |||||||||||||||||
| 言語 | ||||||||||||||||||
| 言語 | eng | |||||||||||||||||
| キーワード | ||||||||||||||||||
| 言語 | en | |||||||||||||||||
| 主題Scheme | Other | |||||||||||||||||
| 主題 | Human identification, Postmortem, Antemortem, Collarbone, Image processing technology, Curvature scale space, Euclidean, Chi-square | |||||||||||||||||
| 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 | departmental bulletin paper | |||||||||||||||||
| 著者 |
Hanni, Cho
× Hanni, Cho× ティ ティ ズイン
WEKO
31575
× 横田, 光広
WEKO
7103
× Shinzawa, Norihiro× Hninn, Aye Thant |
|||||||||||||||||
| 抄録 | ||||||||||||||||||
| 内容記述タイプ | Abstract | |||||||||||||||||
| 内容記述 | In this paper, we propose an approach for matching of CT and X-ray image for identifying the identify of each individual after death. An unknown death body is identified by comparing collarbones of chest CT image after death with the X-ray images before death stored in a database. For decades, doctors or forensic experts accomplished human identification process manually. However, it becomes a burden task for the doctors, and consumes much time, especially in large amount of victims. Therefore, the main purpose of this paper is to save identification time and reduce burden on human experts with the help of computer and image processing technology. We extract the features of each collarbone by using the Curvature Scale Space (CSS) contour-based shape feature extraction method. Then, feature matching process between CT and X-ray images in the database is carried out using Euclidean and Chi-square distance methods, and ranking is performed based on the resulted distance. Finally, the system retrieves the top 15 antemortem X-ray images that are similar to the query image of postmortem CT image of a death person according to the ranked scores. Experiments are conducted on real life dataset collected from the Graduate School of Medicine, University of Miyazaki. To evaluate the accuracy of the proposed system, we make comparative analysis on the results of two distance methods. According to experimental results, the system based on Euclidean distance outperforms the one using Chi-square distance. | |||||||||||||||||
| 言語 | en | |||||||||||||||||
| bibliographic_information |
ja : 宮崎大学工学部紀要 en : Memoirs of Faculty of Engineering, University of Miyazaki 巻 48, p. 103-108, 発行日 2019-07 |
|||||||||||||||||
| 出版者 | ||||||||||||||||||
| 出版者 | 宮崎大学工学部 | |||||||||||||||||
| 言語 | ja | |||||||||||||||||
| 出版者 | ||||||||||||||||||
| 出版者 | Faculty of Engineering, University of Miyazaki | |||||||||||||||||
| 言語 | en | |||||||||||||||||
| ISSN | ||||||||||||||||||
| 収録物識別子タイプ | ISSN | |||||||||||||||||
| 収録物識別子 | 05404924 | |||||||||||||||||
| item_10002_source_id_11 | ||||||||||||||||||
| 収録物識別子タイプ | NCID | |||||||||||||||||
| 収録物識別子 | AA00732558 | |||||||||||||||||
| 出版タイプ | ||||||||||||||||||
| 出版タイプ | VoR | |||||||||||||||||
| 出版タイプResource | http://purl.org/coar/version/c_970fb48d4fbd8a85 | |||||||||||||||||
