Few-shot pill recognition
- Title
- Few-shot pill recognition
- Author
- 김지은
- Keywords
- Image recognition; Text recognition; Image color analysis; Noise measurement; Lighting; Databases; Imaging
- Issue Date
- 2020-06
- Publisher
- Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern
- Citation
- 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), page. 9786-9795
- 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 fewshot 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.
- URI
- https://ieeexplore.ieee.org/document/9157392?arnumber=9157392&SID=EBSCO:edseeehttps://repository.hanyang.ac.kr/handle/20.500.11754/168646
- ISBN
- 978-1-7281-7168-5
- ISSN
- 2575-7075
- DOI
- 10.1109/CVPR42600.2020.00981
- Appears in Collections:
- GRADUATE SCHOOL OF TECHNOLOGY & INNOVATION MANAGEMENT[S](기술경영전문대학원) > TECHNOLOGY MANAGEMENT(기술경영학과) > Articles
- Files in This Item:
There are no files associated with this item.
- Export
- RIS (EndNote)
- XLS (Excel)
- XML