Scaled Dilation of DropBlock Optimization in Convolutional Neural Network for Fungus Classification
Source abstract
Abstract
Image classification always has open challenges for computer vision research. Nowadays, deep learning has promoted the development of this field, especially in Convolutional Neural Networks (CNNs). This article proposes the development of efficiently scaled dilation of DropBlock optimization in CNNs for the fungus classification, which there are five species in this experiment. The proposed technique adjusts the convolution size at 35, 45, and 60 with the max-polling size 2 × 2. The CNNs models are also designed in 12 models with the different BlockSizes and KeepProp. The proposed techniques provide maximum accuracy of 98.30% for the training set. Moreover, three accurate models, called Precision, Recall, and F1-score, are employed to measure the testing set. The experiment results expose that the proposed models achieve to classify the fungus and provide an excellent accuracy compared with the previous techniques. Furthermore, the proposed techniques can reduce the CNNs structure layer, directly affecting resource and time computation.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Cell Image Analysis Techniques · Smart Agriculture and AI · Image Processing Techniques and Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (37)
Show source-provided references
1. Airborne fungi in workplace atmospheres: Overview of active sampling and offline analysis methods used in 2009–201910.1016/B978-0-12-819990-9.00009-3 ↗
2. A fungus spores dataset and a convolutional neural network based approach for fungus detection10.1109/TNB.2018.2839585 ↗
3. The correct nomenclature of zirelí sign in the propaedeutics of pityriasis versicolor10.1016/j.abd.2021.04.004 ↗
4. Superficial infections of the skin and nails10.1016/B978-0-12-809633-8.21015-7 ↗
5. Rhizopus microsporus segmental enteritis in a cow10.1016/j.mmcr.2020.04.002 ↗
6. New species in aspergillus section usti and an overview of aspergillus section cavernicolarum10.1099/ijsem.0.004425 ↗
7. Adrenal paracoccidioidomycosis10.4269/ajtmh.20-0083 ↗
8. Coccidioidomycosis—A fungal disease of the americas
9. The fungus among us: Blastomycosis from spider bites10.1016/j.visj.2020.100825 ↗
10. Aspergillus lung disease10.1016/B978-0-08-102723-3.00116-5 ↗
11. Prevalence of fungi in primary endodontic infections of a Greek-living population through real-time polymerase chain reaction and matrix-assisted laser desorption/ionization time-of-flight mass spectrometry10.1016/j.joen.2021.11.003 ↗
12. Microwave characterization of hydrophilic and hydrophobic plant pathogenic fungi using open-ended coaxial probe10.1109/ACCESS.2019.2908061 ↗
13. Automatic identification of fungi under complex microscopic fecal images10.1117/1.JBO.20.7.076004 ↗
14. Fungus detection through optical sensor system using two different kinds of feature vectors for the classification10.1109/JSEN.2017.2723052 ↗
15. DecoFungi: A web application for automatic characterisation of dye decolorisation in fungal strains10.1186/s12859-018-2082-9 ↗
16. Automatic detection of fungi in microscopic leucorrhea images based on convolutional neural network and morphological method
17. Intelligent identification of microscopic visible components in leucorrhea routine
18. Automatic characterisation of dye decolourisation in fungal strains using expert, traditional, and deep features10.1007/s00500-019-03832-8 ↗
19. Human fungal infection image classification based on convolutional neural network10.1007/978-981-13-9917-6_1 ↗
20. Deep learning approach to description and classification of fungi microscopic images
21. Exploiting convolutional neural network for automatic fungus detection in microscope images
22. Fine-grained multi-instance classification in microscopy through deep attention
23. Aspergillus fumigatus and aspergillosis in 201910.1128/CMR.00140-18 ↗
24. Taxonomy and phylogeny of four new species in absidia (cunninghamellaceae, mucorales) from China10.3389/fmicb.2021.677836 ↗
25. Selection and control efficiency of trichoderma isolates against fusarium oxysporum f. sp. ciceris in Iran10.1016/j.pmpp.2021.101731 ↗
26. Characterization of penicillium s.s. and aspergillus sect. nigri causing postharvest rots of pomegranate fruit in southern Italy10.1016/j.ijfoodmicro.2019.108389 ↗
27. Improving skin-disease classification based on customized loss function combined with balanced mini-batch logic and real-time image augmentation10.1109/ACCESS.2020.3016653 ↗
28. Deep learning based automated diagnosis of skin diseases using dermoscopy
29. Optimized deep learning-inspired model for the diagnosis and prediction of COVID-19
30. Deep learning for smartphone-based malaria parasite detection in thick blood smears10.1109/JBHI.2019.2939121 ↗
31. Deep learning approach for COVID-19 detection in computed tomography images
32. Dropout: A simple way to prevent neural networks from overfitting
33. Efficient object localization using convolutional networks
34. Dropblock: A regularization method for convolutional networks
35. Sequence-dropout block for reducing overfitting problem in image classification10.1109/ACCESS.2020.2983774 ↗
36. Automated firearm classification from bullet markings using deep learning10.1109/ACCESS.2020.2989673 ↗
37. Bird species classification using transfer learning with multistage training