Matches in SemOpenAlex for { <https://semopenalex.org/work/W2997952217> ?p ?o ?g. }
Showing items 1 to 69 of
69
with 100 items per page.
- W2997952217 endingPage "144" @default.
- W2997952217 startingPage "131" @default.
- W2997952217 abstract "Sorting machines use computer vision (CV) to separate food items based on various attributes. For instance, sorting based on size and colour are commonly used in commercial machines. However, detecting external defects using CV remains an open problem. This paper presents an experimental contribution to external defect detection using deep learning. An uncensored dataset with 43,843 images including external defects was built during this study. The dataset is heavily imbalanced towards the healthy class, and it is available online. Deep residual neural network (ResNet) classifiers were trained that are capable of detecting external defects using feature extraction and fine-tuning. The results show that fine-tuning outperformed feature extraction, revealing the benefit of training additional layers when sufficient data samples are available. The best model was a ResNet50 with all its layers fine-tuned. This model achieved an average precision of 94.6 % on the test set. The optimal classifier had a recall of 86.6 % while maintaining a precision of 91.7 % . The posterior class-conditional distributions of the classifier scores showed that the key to classifier success lies in its almost ideal healthy class distribution. The results also explain why the model does not confuse stems/calyxes with external defects. The best model constitutes a milestone for detecting external defects using CV. Because deep learning does not require feature engineering or prior knowledge about the dataset content, the methodology may also work well with other foods." @default.
- W2997952217 created "2020-01-10" @default.
- W2997952217 creator A5006546171 @default.
- W2997952217 creator A5039449516 @default.
- W2997952217 creator A5044666957 @default.
- W2997952217 date "2020-02-01" @default.
- W2997952217 modified "2023-10-10" @default.
- W2997952217 title "Computer vision based detection of external defects on tomatoes using deep learning" @default.
- W2997952217 cites W1845160027 @default.
- W2997952217 cites W2018620632 @default.
- W2997952217 cites W2019115728 @default.
- W2997952217 cites W2026978702 @default.
- W2997952217 cites W2057175907 @default.
- W2997952217 cites W2091987367 @default.
- W2997952217 cites W2129152340 @default.
- W2997952217 cites W2179628444 @default.
- W2997952217 cites W2384494701 @default.
- W2997952217 cites W2467433404 @default.
- W2997952217 cites W2520364485 @default.
- W2997952217 cites W2614850301 @default.
- W2997952217 cites W2731165298 @default.
- W2997952217 cites W2767767563 @default.
- W2997952217 cites W2790979755 @default.
- W2997952217 cites W2893240771 @default.
- W2997952217 cites W2919115771 @default.
- W2997952217 doi "https://doi.org/10.1016/j.biosystemseng.2019.12.003" @default.
- W2997952217 hasPublicationYear "2020" @default.
- W2997952217 type Work @default.
- W2997952217 sameAs 2997952217 @default.
- W2997952217 citedByCount "103" @default.
- W2997952217 countsByYear W29979522172020 @default.
- W2997952217 countsByYear W29979522172021 @default.
- W2997952217 countsByYear W29979522172022 @default.
- W2997952217 countsByYear W29979522172023 @default.
- W2997952217 crossrefType "journal-article" @default.
- W2997952217 hasAuthorship W2997952217A5006546171 @default.
- W2997952217 hasAuthorship W2997952217A5039449516 @default.
- W2997952217 hasAuthorship W2997952217A5044666957 @default.
- W2997952217 hasConcept C108583219 @default.
- W2997952217 hasConcept C127413603 @default.
- W2997952217 hasConcept C154945302 @default.
- W2997952217 hasConcept C31972630 @default.
- W2997952217 hasConcept C41008148 @default.
- W2997952217 hasConceptScore W2997952217C108583219 @default.
- W2997952217 hasConceptScore W2997952217C127413603 @default.
- W2997952217 hasConceptScore W2997952217C154945302 @default.
- W2997952217 hasConceptScore W2997952217C31972630 @default.
- W2997952217 hasConceptScore W2997952217C41008148 @default.
- W2997952217 hasFunder F4320322025 @default.
- W2997952217 hasLocation W29979522171 @default.
- W2997952217 hasOpenAccess W2997952217 @default.
- W2997952217 hasPrimaryLocation W29979522171 @default.
- W2997952217 hasRelatedWork W1891287906 @default.
- W2997952217 hasRelatedWork W1969923398 @default.
- W2997952217 hasRelatedWork W2036807459 @default.
- W2997952217 hasRelatedWork W2731899572 @default.
- W2997952217 hasRelatedWork W2755342338 @default.
- W2997952217 hasRelatedWork W2772917594 @default.
- W2997952217 hasRelatedWork W2899084033 @default.
- W2997952217 hasRelatedWork W2939353110 @default.
- W2997952217 hasRelatedWork W3009238340 @default.
- W2997952217 hasRelatedWork W3215138031 @default.
- W2997952217 hasVolume "190" @default.
- W2997952217 isParatext "false" @default.
- W2997952217 isRetracted "false" @default.
- W2997952217 magId "2997952217" @default.
- W2997952217 workType "article" @default.