Matches in SemOpenAlex for { <https://semopenalex.org/work/W3193440158> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W3193440158 endingPage "801" @default.
- W3193440158 startingPage "789" @default.
- W3193440158 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." @default.
- W3193440158 created "2021-08-30" @default.
- W3193440158 creator A5009646148 @default.
- W3193440158 creator A5023278205 @default.
- W3193440158 creator A5036317972 @default.
- W3193440158 creator A5065893759 @default.
- W3193440158 date "2021-08-26" @default.
- W3193440158 modified "2023-10-03" @default.
- W3193440158 title "Deep Learning-Based Automatic Detection of Defective Tablets in Pharmaceutical Manufacturing" @default.
- W3193440158 cites W1861492603 @default.
- W3193440158 cites W2028524042 @default.
- W3193440158 cites W2031489346 @default.
- W3193440158 cites W2042373716 @default.
- W3193440158 cites W2065581624 @default.
- W3193440158 cites W2069087061 @default.
- W3193440158 cites W2117539524 @default.
- W3193440158 cites W2194775991 @default.
- W3193440158 cites W2333882152 @default.
- W3193440158 cites W2802519909 @default.
- W3193440158 cites W2906448818 @default.
- W3193440158 cites W2912815642 @default.
- W3193440158 cites W2917127475 @default.
- W3193440158 cites W2945434083 @default.
- W3193440158 cites W2963446712 @default.
- W3193440158 cites W2965127303 @default.
- W3193440158 cites W2980305256 @default.
- W3193440158 cites W3006802743 @default.
- W3193440158 cites W3011416893 @default.
- W3193440158 cites W3104156061 @default.
- W3193440158 doi "https://doi.org/10.1007/978-3-030-75506-5_64" @default.
- W3193440158 hasPublicationYear "2021" @default.
- W3193440158 type Work @default.
- W3193440158 sameAs 3193440158 @default.
- W3193440158 citedByCount "1" @default.
- W3193440158 countsByYear W31934401582023 @default.
- W3193440158 crossrefType "book-chapter" @default.
- W3193440158 hasAuthorship W3193440158A5009646148 @default.
- W3193440158 hasAuthorship W3193440158A5023278205 @default.
- W3193440158 hasAuthorship W3193440158A5036317972 @default.
- W3193440158 hasAuthorship W3193440158A5065893759 @default.
- W3193440158 hasConcept C108583219 @default.
- W3193440158 hasConcept C119857082 @default.
- W3193440158 hasConcept C12267149 @default.
- W3193440158 hasConcept C141404830 @default.
- W3193440158 hasConcept C150899416 @default.
- W3193440158 hasConcept C153180895 @default.
- W3193440158 hasConcept C154945302 @default.
- W3193440158 hasConcept C177264268 @default.
- W3193440158 hasConcept C199360897 @default.
- W3193440158 hasConcept C41008148 @default.
- W3193440158 hasConcept C81363708 @default.
- W3193440158 hasConcept C8642999 @default.
- W3193440158 hasConceptScore W3193440158C108583219 @default.
- W3193440158 hasConceptScore W3193440158C119857082 @default.
- W3193440158 hasConceptScore W3193440158C12267149 @default.
- W3193440158 hasConceptScore W3193440158C141404830 @default.
- W3193440158 hasConceptScore W3193440158C150899416 @default.
- W3193440158 hasConceptScore W3193440158C153180895 @default.
- W3193440158 hasConceptScore W3193440158C154945302 @default.
- W3193440158 hasConceptScore W3193440158C177264268 @default.
- W3193440158 hasConceptScore W3193440158C199360897 @default.
- W3193440158 hasConceptScore W3193440158C41008148 @default.
- W3193440158 hasConceptScore W3193440158C81363708 @default.
- W3193440158 hasConceptScore W3193440158C8642999 @default.
- W3193440158 hasLocation W31934401581 @default.
- W3193440158 hasOpenAccess W3193440158 @default.
- W3193440158 hasPrimaryLocation W31934401581 @default.
- W3193440158 hasRelatedWork W1996541855 @default.
- W3193440158 hasRelatedWork W3018421652 @default.
- W3193440158 hasRelatedWork W3021430260 @default.
- W3193440158 hasRelatedWork W3091976719 @default.
- W3193440158 hasRelatedWork W3192840557 @default.
- W3193440158 hasRelatedWork W4220996320 @default.
- W3193440158 hasRelatedWork W4285149559 @default.
- W3193440158 hasRelatedWork W4312200629 @default.
- W3193440158 hasRelatedWork W4380894485 @default.
- W3193440158 hasRelatedWork W4382286161 @default.
- W3193440158 isParatext "false" @default.
- W3193440158 isRetracted "false" @default.
- W3193440158 magId "3193440158" @default.
- W3193440158 workType "book-chapter" @default.