Browse > Article
http://dx.doi.org/10.9717/kmms.2019.22.3.349

Comparison and Verification of Deep Learning Models for Automatic Recognition of Pills  

Yi, GyeongYun (Dept. of Biomedical Eng., Gachon University College of Medicine)
Kim, YoungJae (Dept. of Biomedical Eng., Gachon University College of Medicine)
Kim, SeongTae (Dept. of Pharmacy., Gil Hospital)
Kim, HyoEun (Dept. of Biomedical Eng., Gachon University College of Medicine)
Kim, KwangGi (Dept. of Biomedical Eng., Gachon University College of Medicine)
Publication Information
Journal of Korea Multimedia Society / v.22, no.3, 2019 , pp. 349-356 More about this Journal
Abstract
When a prescription change occurs in the hospital depending on a patient's improvement status, pharmacists directly classify manually returned pills which are not taken by a patient. There are hundreds of kinds of pills to classify. Because it is manual, mistakes can occur and which can lead to medical accidents. In this study, we have compared YOLO, Faster R-CNN and RetinaNet to classify and detect pills. The data consisted of 10 classes and used 100 images per class. To evaluate the performance of each model, we used cross-validation. As a result, the YOLO Model had sensitivity of 91.05%, FPs/image of 0.0507. The Faster R-CNN's sensitivity was 99.6% and FPs/image was 0.0089. The RetinaNet showed sensitivity of 98.31% and FPs/image of 0.0119. Faster RCNN showed the best performance among these three models tested. Thus, the most appropriate model for classifying pills among the three models is the Faster R-CNN with the most accurate detection and classification results and a low FP/image.
Keywords
Pill Classification; Object Detection; Deep Learning; Artificial Intelligent; Hospital;
Citations & Related Records
Times Cited By KSCI : 1  (Citation Analysis)
연도 인용수 순위
1 B.K. Lee and S.G. Kwon, "Automatic Classification System of Tablets with Various Colors and Shapes," Journal of Korea Multimedia Society, pp. 659-666, Vol. 21, No. 6, 2018.   DOI
2 Y.B. Lee, Matching and Retrieval of Drug Pill Images, Master's Thesis of Korea University, 2011.
3 A. Krizhevsky, I. Sutskever, and G.E. Hinton, "Imagenet Classification with Deep Convolutional Neural Networks," Advances in Neural Information Processing Systems, pp. 1097-1105, Vol. 60, No. 6, 2012.
4 B.Y. Yoo, W.H. Hwang, S.J. Han, S.M. Rhee, J.B. Kim, J.J. Han, et al., "The Trend of Image Recognition Close to The Human Level in Deep Learning," Communications of the Korean Institute of Information Scientists and Engineers, pp. 32-41, Vol. 33, No. 9, 2015.
5 D.U. Kim, Shape and Text Imprint Recognition of Pill Image Taken with a Smartphone, Master's Thesis of Seoul National University, 2017.
6 R. Joseph, D. Santosh, G. Ross, and F. Ali, "You Only Look Once: Unified, Real-Time Object Detection," Proceeding of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779-788, 2016.
7 YOLO: Real-Time Object Detection, https://pjreddie.com/darknet/yolo/ (accessed May, 21, 2018).
8 How to Train YOLOv2 to Detect Custom Objects, https://timebutt.github.io/static/how-to-train-yolov2-to-detect-custom-objects/ (accessed May, 25, 2018).
9 Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, "Gradient-Based Learning Applied to Document Recognition," Proceedings of the IEEE, Vol. 86, No. 11, pp. 2278-2324, 1998.   DOI
10 D.A. Forsyth, J.L. Mundy, V.D. Gesu, R. Cipolla, Shape, Contour and Grouping in Computer Vision, Springer Verlag, Berlin, Heidelberg.., 1999.
11 R. Girshick, "Fast R-CNN," Proceedings of the IEEE International Conference on Computer Vision, pp. 1440-1448, 2015.
12 S. Ren, K. He, R. Girshick, and J. Sun "Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks," Advances in Neural Information Processing Systems, pp. 91-99, Vol. 39, No. 6, 2015.
13 K. He, X. Zhang, S. Ren, and J. Sun, "Deep Residual Learning for Image Recognition," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770-778, 2016.
14 T.Y. Lin, P. Goyal, R. Girshick, K. He, and P. Dollar, "Focal Loss for Dense Object Detection," In 2017 IEEE International Conference on Computer Vision (ICCV), pp. 2999-3007, 2017.
15 F. Ahmed, D. Tarlow, and D. Batra, "Optimizing Expected Intersection-over-union with Candidate-constrained CRFs," Proceedings of the IEEE International Conference on Computer Vision, pp. 1850-1858, 2015.
16 K.S. Song, H.S. Kang, J.G. Im, M.C. Chung, C.W. Kim, J.H. Kim, et al., "Effects of Digital Image Processing on the Detection of Simulated Lesions in Chest Radiographs: An Experimental Study," Journal of Korean Radiological Society, Vol. 28, No. 6, pp. 858-864, 1992.   DOI
17 LeCun, Yann, et al. "Object recognition with gradient-based learning." Shape, contour and grouping in computer vision. Springer, Berlin, Heidelberg., 1999. 319-345.