Pill recognition using imprint information by two-step sampling distance sets

Jiye Yu, Zhiyuan Chen, Seiichiro Kamata

Research output: Chapter in Book/Report/Conference proceedingConference contribution

8 Citations (Scopus)

Abstract

Huge variety of medicine cures diseases. But unlabeled pills sometimes confuse people, even causing adverse drug events. This paper introduces a high accuracy automatic pill recognition method based on pill imprint which is a main discriminative factor between different pills. To describe the imprint information clearly, we propose a Two-step Sampling Distance Sets (TSDS) descriptor based on Distance Sets (DS) using a two-step sampling strategy. The two-step sampling strategy applies a resampling according to imprint segmentation, which divides an imprint into separated strokes, fragments and noise points. The TSDS is able to take control over the selection of feature points, aiming to cut down the noise points and unwished fragments generated by imprint extraction which will cause disturbance on recognition. In the aspect of the imprint extraction, we preprocess the pill image by dynamic contrast adjustment to cope with the exposure problem. Modified Stroke Width Transform (MSWT) is used to extract the imprint by detecting the coherent strokes on the pill. Finally, several experimental results have shown 86.01%, rank-1 matching accuracy, and 93.64%, within top 5 ranks, when classifying pills into 2500 categories.

Original languageEnglish
Title of host publicationProceedings - International Conference on Pattern Recognition
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages3156-3161
Number of pages6
ISBN (Print)9781479952083
DOIs
Publication statusPublished - 2014 Dec 4
Event22nd International Conference on Pattern Recognition, ICPR 2014 - Stockholm
Duration: 2014 Aug 242014 Aug 28

Other

Other22nd International Conference on Pattern Recognition, ICPR 2014
CityStockholm
Period14/8/2414/8/28

Fingerprint

Sampling
Medicine
Mathematical transformations

Keywords

  • Image retrieval
  • Imprint extraction
  • Pill recognition
  • Two-step Sampling Distance Sets (TSDS)

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Yu, J., Chen, Z., & Kamata, S. (2014). Pill recognition using imprint information by two-step sampling distance sets. In Proceedings - International Conference on Pattern Recognition (pp. 3156-3161). [6977256] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICPR.2014.544

Pill recognition using imprint information by two-step sampling distance sets. / Yu, Jiye; Chen, Zhiyuan; Kamata, Seiichiro.

Proceedings - International Conference on Pattern Recognition. Institute of Electrical and Electronics Engineers Inc., 2014. p. 3156-3161 6977256.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Yu, J, Chen, Z & Kamata, S 2014, Pill recognition using imprint information by two-step sampling distance sets. in Proceedings - International Conference on Pattern Recognition., 6977256, Institute of Electrical and Electronics Engineers Inc., pp. 3156-3161, 22nd International Conference on Pattern Recognition, ICPR 2014, Stockholm, 14/8/24. https://doi.org/10.1109/ICPR.2014.544
Yu J, Chen Z, Kamata S. Pill recognition using imprint information by two-step sampling distance sets. In Proceedings - International Conference on Pattern Recognition. Institute of Electrical and Electronics Engineers Inc. 2014. p. 3156-3161. 6977256 https://doi.org/10.1109/ICPR.2014.544
Yu, Jiye ; Chen, Zhiyuan ; Kamata, Seiichiro. / Pill recognition using imprint information by two-step sampling distance sets. Proceedings - International Conference on Pattern Recognition. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 3156-3161
@inproceedings{c7972c888e1744d8bfc2b95edf1899dd,
title = "Pill recognition using imprint information by two-step sampling distance sets",
abstract = "Huge variety of medicine cures diseases. But unlabeled pills sometimes confuse people, even causing adverse drug events. This paper introduces a high accuracy automatic pill recognition method based on pill imprint which is a main discriminative factor between different pills. To describe the imprint information clearly, we propose a Two-step Sampling Distance Sets (TSDS) descriptor based on Distance Sets (DS) using a two-step sampling strategy. The two-step sampling strategy applies a resampling according to imprint segmentation, which divides an imprint into separated strokes, fragments and noise points. The TSDS is able to take control over the selection of feature points, aiming to cut down the noise points and unwished fragments generated by imprint extraction which will cause disturbance on recognition. In the aspect of the imprint extraction, we preprocess the pill image by dynamic contrast adjustment to cope with the exposure problem. Modified Stroke Width Transform (MSWT) is used to extract the imprint by detecting the coherent strokes on the pill. Finally, several experimental results have shown 86.01{\%}, rank-1 matching accuracy, and 93.64{\%}, within top 5 ranks, when classifying pills into 2500 categories.",
keywords = "Image retrieval, Imprint extraction, Pill recognition, Two-step Sampling Distance Sets (TSDS)",
author = "Jiye Yu and Zhiyuan Chen and Seiichiro Kamata",
year = "2014",
month = "12",
day = "4",
doi = "10.1109/ICPR.2014.544",
language = "English",
isbn = "9781479952083",
pages = "3156--3161",
booktitle = "Proceedings - International Conference on Pattern Recognition",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Pill recognition using imprint information by two-step sampling distance sets

AU - Yu, Jiye

AU - Chen, Zhiyuan

AU - Kamata, Seiichiro

PY - 2014/12/4

Y1 - 2014/12/4

N2 - Huge variety of medicine cures diseases. But unlabeled pills sometimes confuse people, even causing adverse drug events. This paper introduces a high accuracy automatic pill recognition method based on pill imprint which is a main discriminative factor between different pills. To describe the imprint information clearly, we propose a Two-step Sampling Distance Sets (TSDS) descriptor based on Distance Sets (DS) using a two-step sampling strategy. The two-step sampling strategy applies a resampling according to imprint segmentation, which divides an imprint into separated strokes, fragments and noise points. The TSDS is able to take control over the selection of feature points, aiming to cut down the noise points and unwished fragments generated by imprint extraction which will cause disturbance on recognition. In the aspect of the imprint extraction, we preprocess the pill image by dynamic contrast adjustment to cope with the exposure problem. Modified Stroke Width Transform (MSWT) is used to extract the imprint by detecting the coherent strokes on the pill. Finally, several experimental results have shown 86.01%, rank-1 matching accuracy, and 93.64%, within top 5 ranks, when classifying pills into 2500 categories.

AB - Huge variety of medicine cures diseases. But unlabeled pills sometimes confuse people, even causing adverse drug events. This paper introduces a high accuracy automatic pill recognition method based on pill imprint which is a main discriminative factor between different pills. To describe the imprint information clearly, we propose a Two-step Sampling Distance Sets (TSDS) descriptor based on Distance Sets (DS) using a two-step sampling strategy. The two-step sampling strategy applies a resampling according to imprint segmentation, which divides an imprint into separated strokes, fragments and noise points. The TSDS is able to take control over the selection of feature points, aiming to cut down the noise points and unwished fragments generated by imprint extraction which will cause disturbance on recognition. In the aspect of the imprint extraction, we preprocess the pill image by dynamic contrast adjustment to cope with the exposure problem. Modified Stroke Width Transform (MSWT) is used to extract the imprint by detecting the coherent strokes on the pill. Finally, several experimental results have shown 86.01%, rank-1 matching accuracy, and 93.64%, within top 5 ranks, when classifying pills into 2500 categories.

KW - Image retrieval

KW - Imprint extraction

KW - Pill recognition

KW - Two-step Sampling Distance Sets (TSDS)

UR - http://www.scopus.com/inward/record.url?scp=84919880812&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84919880812&partnerID=8YFLogxK

U2 - 10.1109/ICPR.2014.544

DO - 10.1109/ICPR.2014.544

M3 - Conference contribution

AN - SCOPUS:84919880812

SN - 9781479952083

SP - 3156

EP - 3161

BT - Proceedings - International Conference on Pattern Recognition

PB - Institute of Electrical and Electronics Engineers Inc.

ER -