| 書目名稱 | From Global to Local Statistical Shape Priors |
| 副標(biāo)題 | Novel Methods to Obt |
| 編輯 | Carsten Last |
| 視頻video | http://file.papertrans.cn/349/348698/348698.mp4 |
| 概述 | Is understandable, readable, and well-structured with numerous illustrations.Presents interesting, new, and powerful concepts.Serves as a “gateway drug” to the field thanks to its unique presentation |
| 叢書名稱 | Studies in Systems, Decision and Control |
| 圖書封面 |  |
| 描述 | This book proposes a new approach to handle the problem of limited training data. Common approaches to cope with this problem are to model the shape variability independently across predefined segments or to allow artificial shape variations that cannot be explained through the training data, both of which have their drawbacks. The approach presented uses a local shape prior in each element of the underlying data domain and couples all local shape priors via smoothness constraints. The book provides a sound mathematical foundation in order to embed this new shape prior formulation into the well-known variational image segmentation framework. The new segmentation approach so obtained allows accurate reconstruction of even complex object classes with only a few training shapes at hand. |
| 出版日期 | Book 2017 |
| 關(guān)鍵詞 | Global Statistical Shape Priors; Pattern Recognition; Image Processing; Computer Vision; Object Segmenta |
| 版次 | 1 |
| doi | https://doi.org/10.1007/978-3-319-53508-1 |
| isbn_softcover | 978-3-319-85169-3 |
| isbn_ebook | 978-3-319-53508-1Series ISSN 2198-4182 Series E-ISSN 2198-4190 |
| issn_series | 2198-4182 |
| copyright | Springer International Publishing AG 2017 |
|Archiver|手機版|小黑屋|
派博傳思國際
( 京公網(wǎng)安備110108008328)
GMT+8, 2025-10-5 09:26
發(fā)表于 2025-3-21 17:02:07
