Abstract
With many tablets produced everyday in manufacturing plants, the pharmaceutical industry needs automatic, highly accurate methods for inspection of tablet quality. Detecting defective tablets is of importance to reduce unqualified products to consumers. In this paper, we propose a deep learning method combining image processing and deep convolutional neural networks (DCNN) for detection of defective tablets using images captured by a multiple-camera inspection system. A dataset of 6000 images of tablets labelled either GOOD or NOT-GOOD were collected at a pharmaceutical factory using commercial camera inspection systems. After collecting and labelling, the images were preprocessed to normalize intensity values. The entire dataset was split into a training set (50%, 3000 images), a validation set (16.6%, 1000 images) and a testing set (33.3%, 2000 images). We trained DCNN ResNets (ResNet50, ResNet101) and DenseNets (DenseNet169, DenseNet201) models on the training set and validated them on the validation set. We applied transfer learning techniques by using pre-trained models that had been trained on the ImageNet dataset in combination with data augmentation and training strategies such as learning rate rescheduling overtime. We compared our deep learning methods with various machine-learning ones such as Support Vector Machine (SVM), K-Nearest-Neighbors (KNN), AdaBoost that used intensity histograms as features. Tuning hyperparameters were performed to seek the best hyper-parameters and algorithms. We achieved best performances using the deep learning models as the ResNet50, and DenseNet169 obtained 96.60% ± 4.9% and 94.13% ± 4.2% accuracies (ACC), respectively. In contrast, SVM achieved 87.75% ACC, KNN achieved 76.09% ± 7.7% ACC while AdaBoost achieved 81.25% ACC, respectively.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Albion K, Briens L, Briens C, Berruti F (2006) Detection of the breakage of pharmaceutical tablets in pneumatic transport. Int J Pharm 322(1–2)
Sabri AH, Hallam CN, Baker NA, Murphy DS, Gabbott IP (2018) Understanding tablet defects in commercial manufacture and transfer. J Drug Deliv Sci Technol 46:1–6. https://doi.org/10.1016/j.jddst.2018.04.020
Možina M, Tomaževič D, Pernuš F, Likar B (2013) Automated visual inspection of imprint quality of pharmaceutical tablets. Mach Vis Appl 24(1):63–73. https://doi.org/10.1007/s00138-011-0366-4
Možina M, Tomaževič D, Pernuš F, Likar B (2011) Real-time image segmentation for visual inspection of pharmaceutical tablets. Mach Vis Appl 22(1):145–156. https://doi.org/10.1007/s00138-009-0218-7
Manzoor H, Randhawa YS (2014) Edge detection in digital image using statistical method. IOSR J Electron Commun Eng 9(3):15–19. https://doi.org/10.9790/2834-09311519
Voulodimos A, Doulamis N, Doulamis A, Protopapadakis E (2018) Deep learning for computer vision: a brief review. Comput Intell Neurosci 2018:7068349
Špiclin Ž, Bukovec M, Pernuš F, Likar B (2011) Image registration for visual inspection of imprinted pharmaceutical tablets. Mach Vis Appl 22(1):197–206. https://doi.org/10.1007/s00138-007-0104-0
Nguyen DT, Ryu S, Qureshi MNI, Choi M, Lee KH, Lee B (2019) Hybrid multivariate pattern analysis combined with extreme learning machine for Alzheimer’s dementia diagnosis using multi-measure rs-fMRI spatial patterns. PLoS One 14(2):e0212582
Duc NT, Lee B (2019) Microstate functional connectivity in EEG cognitive tasks revealed by a multivariate Gaussian hidden Markov model with phase locking value. J Neural Eng 16(2):026033
Duc NT, Ryu S, Choi M, Iqbal Qureshi MN, Lee B (2019) Mild cognitive impairment diagnosis using extreme learning machine combined with multivoxel pattern analysis on multi-biomarker resting-state FMRI. In: Conference proceedings IEEE engineering in medicine and biology society, vol 2019, pp 882–885
Kato N, Inoue M, Nishiyama M, Iwai Y (2020) Comparing the recognition accuracy of humans and deep learning on a simple visual inspection task. Lecture notes in computer science, pp 184–197. http://doi.org/10.1007/978-3-030-41299-9_15
Nagata F et al (2018) Basic application of deep convolutional neural network to visual inspection. In: Proceedings of the 6th IIAE international conference on industrial application engineering 2018. http://doi.org/10.12792/iciae2018.004
Duc NT, Ryu S, Qureshi MNI, Choi M, Lee KH, Lee B (2020) 3D-deep learning based automatic diagnosis of Alzheimer’s disease with joint MMSE prediction using resting-state fMRI. Neuroinformatics 18(1):71–86
Tabernik D, Šela S, Skvarč J, Skočaj D (2019) Segmentation-based deep-learning approach for surface-defect detection. J Intell Manuf. https://doi.org/10.1007/s10845-019-01476-x
Russakovsky O et al (2015) ImageNet large scale visual recognition challenge. Int J Comput Vision 115(3):211–252. https://doi.org/10.1007/s11263-015-0816-y
Everingham M, Van Gool L, Williams CKI, Winn J, Zisserman A (2010) The pascal visual object classes (VOC) challenge. Int J Comput Vision 88(2):303–338. https://doi.org/10.1007/s11263-009-0275-4
Lin T-Y et al (2014) Microsoft COCO: common objects in context. In: Computer vision—ECCV 2014, pp 740–755. http://doi.org/10.1007/978-3-319-10602-1_48
On the difficulty of training recurrent neural networks. https://arxiv.org/pdf/1211.5063.pdf. Accessed 27 Apr 2020
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR). http://doi.org/10.1109/cvpr.2016.90
Highway Networks. https://arxiv.org/abs/1505.00387. Accessed 27 Apr 2020
Kim YD et al (2020) Effects of hypertension, diabetes, and smoking on age and sex prediction from retinal fundus images. Sci Rep 10(1). http://doi.org/10.1038/s41598-020-61519-9
Huang G, Liu Z, Van Der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR). http://doi.org/10.1109/cvpr.2017.243
Perez H, Tah JHM, Mosavi A (2019) Deep learning for detecting building defects using convolutional neural networks. Sensors 19(16). http://doi.org/10.3390/s19163556
Conflicts of Interest
The authors have no conflict of interest to declare.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Quan, H.T., Huy, D.D., Hoan, N.T., Duc, N.T. (2022). Deep Learning-Based Automatic Detection of Defective Tablets in Pharmaceutical Manufacturing. In: Van Toi, V., Nguyen, TH., Long, V.B., Huong, H.T.T. (eds) 8th International Conference on the Development of Biomedical Engineering in Vietnam. BME 2020. IFMBE Proceedings, vol 85. Springer, Cham. https://doi.org/10.1007/978-3-030-75506-5_64
Download citation
DOI: https://doi.org/10.1007/978-3-030-75506-5_64
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-75505-8
Online ISBN: 978-3-030-75506-5
eBook Packages: EngineeringEngineering (R0)