Few-shot pill recognition
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Ling, Suiyi | - |
dc.contributor.author | Pastor, Andreas | - |
dc.contributor.author | Li, Jing | - |
dc.contributor.author | Che, Zhaohui | - |
dc.contributor.author | Wang, Junle | - |
dc.contributor.author | Kim, Ji Eun | - |
dc.contributor.author | Le, Callet Patirck | - |
dc.date.accessioned | 2022-07-08T00:24:08Z | - |
dc.date.available | 2022-07-08T00:24:08Z | - |
dc.date.issued | 2020-06 | - |
dc.identifier.issn | 1063-6919 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/145559 | - |
dc.description.abstract | Pill image recognition is vital for many personal/public health-care applications and should be robust to diverse unconstrained real-world conditions. Most existing pill recognition models are limited in tackling this challenging few-shot learning problem due to the insufficient instances per category. With limited training data, neural network based models have limitations in discovering most discriminating features, or going deeper. Especially, existing models fail to handle the hard samples taken under less controlled imaging conditions. In this study, a new pill image database, namely CURE, is first developed with more varied imaging conditions and instances for each pill category. Secondly, a light-weight W2-net is proposed for better pill segmentation. Thirdly, a Multi-Stream (MS) deep network that captures task-related features along with a novel two-stage training methodology are proposed. Within the proposed framework, a Batch All strategy that considers all the samples is first employed for the sub-streams, and then a Batch Hard strategy that considers only the hard samples mined in the first stage is utilized for the fusion network. By doing so, complex samples that could not be represented by one type of feature could be focused and the model could be forced to exploit other domain-related information more effectively. Experiment results show that the proposed model outperforms state-of-the-art models on both the National Institute of Health (NIH) and our CURE database. | - |
dc.format.extent | 10 | - |
dc.language | 영어 | - |
dc.language.iso | ENG | - |
dc.publisher | IEEE Computer Society | - |
dc.title | Few-shot pill recognition | - |
dc.type | Article | - |
dc.publisher.location | 미국 | - |
dc.identifier.doi | 10.1109/CVPR42600.2020.00981 | - |
dc.identifier.scopusid | 2-s2.0-85094644629 | - |
dc.identifier.bibliographicCitation | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp 9786 - 9795 | - |
dc.citation.title | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition | - |
dc.citation.startPage | 9786 | - |
dc.citation.endPage | 9795 | - |
dc.type.docType | Conference Paper | - |
dc.description.isOpenAccess | N | - |
dc.description.journalRegisteredClass | scopus | - |
dc.subject.keywordPlus | Image recognition | - |
dc.subject.keywordPlus | Complex samples | - |
dc.subject.keywordPlus | Health care application | - |
dc.subject.keywordPlus | Imaging conditions | - |
dc.subject.keywordPlus | Learning problem | - |
dc.subject.keywordPlus | Limited training data | - |
dc.subject.keywordPlus | National institute of healths | - |
dc.subject.keywordPlus | Recognition models | - |
dc.subject.keywordPlus | State of the art | - |
dc.subject.keywordPlus | Curing | - |
dc.identifier.url | https://ieeexplore.ieee.org/document/9157392 | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
222, Wangsimni-ro, Seongdong-gu, Seoul, 04763, Korea+82-2-2220-1365
COPYRIGHT © 2021 HANYANG UNIVERSITY.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.