TOWARDS IMPROVED DISEASE IDENTIFICATION WITH PRETRAINED CONVOLUTIONAL NEURAL NETWORKS AS FEATURE EXTRACTORS FOR CHILI LEAF IMAGES

Nuramin Fitri Aminuddin; Herdawatie Abdul Kadir; Mohd Razali Md Tomari; Ariffuddin Joret; Zarina Tukiran

doi:10.11113/jurnalteknologi.v86.19853

Authors

Nuramin Fitri Aminuddin Department of Electronic Engineering, Faculty of Electrical and Electronic Engineering, Universiti Tun Hussein Onn Malaysia, Batu Pahat, 86400, Johor, Malaysia https://orcid.org/0000-0002-9816-5238
Herdawatie Abdul Kadir Department of Electronic Engineering, Faculty of Electrical and Electronic Engineering, Universiti Tun Hussein Onn Malaysia, Batu Pahat, 86400, Johor, Malaysia
Mohd Razali Md Tomari Department of Electronic Engineering, Faculty of Electrical and Electronic Engineering, Universiti Tun Hussein Onn Malaysia, Batu Pahat, 86400, Johor, Malaysia https://orcid.org/0000-0002-9850-7445
Ariffuddin Joret Department of Electronic Engineering, Faculty of Electrical and Electronic Engineering, Universiti Tun Hussein Onn Malaysia, Batu Pahat, 86400, Johor, Malaysia https://orcid.org/0000-0002-3160-9674
Zarina Tukiran Department of Electronic Engineering, Faculty of Electrical and Electronic Engineering, Universiti Tun Hussein Onn Malaysia, Batu Pahat, 86400, Johor, Malaysia

DOI:

https://doi.org/10.11113/jurnalteknologi.v86.19853

Keywords:

Diseased, chili leaf, pretrained, convolutional neural networks, cross-validation

Abstract

Chili is a popular crop that is widely grown due to its flavorful and spicy fruit that is nutritionally beneficial. For the benefit of economic growth, it is important to precisely assess the chili health. With the advancement of computer vision-based applications, methods such as feature descriptors have been utilized to assist farm owners in identifying chili diseases via chili leaf images. However, these feature descriptors still require the manual extraction of disease features in order to accurately identify chili diseases. In this research, pretrained Convolutional Neural Networks (CNNs) are proposed as feature extractors to identify healthy and diseased chili leaf images. Three pretrained CNN models, DenseNet-201, EfficientNet-b0, and NasNet-Mobile, are utilized for their ability to identify healthy and diseased chili leaf using five indexes: accuracy, recall, specificity, precision, and F1-score. These indexes are validated through a five-fold cross-validation method during the experiments. The experimental results show that the EfficientNet-b0 model achieved the highest identification performance, with indexes of accuracy, recall, specificity, precision, and F1-score of 97.05%, 0.97, 0.92, 0.92, and 0.94, respectively. Therefore, the use of pretrained CNNs as feature extractors has the capability to enhance the efficiency and accuracy of chili disease identification in agricultural settings.

References

Thakur, H., Jindal, S., Sharma, A., and Dhaliwal, M. 2019. A Monogenic Dominant Resistance for Leaf Curl Virus Disease in Chilli Pepper (Capsicum annuum L.). Crop Protection. 116: 115-120.

Doi: https://doi.org/10.1016/j.cropro.2018.10.007.

Colney, L., Tyagi, W., and Rai, M. 2018. Morphological and Molecular Characterization of Two Distinct Chilli Cultivars from North Eastern India with Special Reference to Pungency Related Genes. Scientia Horticulturae. 240: 1-10. Doi: https://doi.org/10.1016/j.scia.2018.05.045.

Lu, M., Chen, C., Lan, Y., Xiao, J., Li, R., Huang, J., Huang, Q., Cao, Y., and Ho, C. T. 2020. Capsaicin - The Major Bioactive Ingredient of Chili Peppers: Bio-Efficacy and Delivery Systems. Food & Function. 11(4): 2848-2860. Doi: https://doi.org/10.1039/d0fo00351d.

Dhingra, G., Kumar, V., and Joshi, H. D. 2017. Study of Digital Image Processing Techniques for Leaf Disease Detection and Classification. Multimedia Tools and Applications. 77(15): 19951-20000. Doi: https://doi.org/10.1007/s11042-017-5445-8.

Özaydın, U., Georgiou, T., and Lew, M. 2019. A Comparison of CNN and Classic Features for Image Retrieval. Contemporary Multimedia Index. 1-4. Doi: https://doi.org/10.48550/arXiv.1908.09300.

Sufola, D., Malemathh, V., and Sundaram, K. M. 2021. Affine Invariant Approach for Disease Detection on Chili Plant. Electrical, Computer and Energy Technologies. Doi: https://doi.org/10.1109/icecet52533.2021.9698472.

Sari, Y., Baskara, A. R., and Wahyuni, R. 2021. Classification of Chili Leaf Disease Using the Gray Level Co-occurrence Matrix (GLCM) and the Support Vector Machine (SVM) Methods. Informatics and Computing. Doi: https://doi.org/10.1109/icic54025.2021.9632920.

Devi, B. M., and Amarendra, K. 2020. Machine Learning Based Application to Detect Pepper Leaf Diseases Using HistGradientBoosting Classifier with Fused HOG and LBP Features. Engineering Research. 8(10): 7371-7376. Doi: https://doi.org/10.30534/ijeter/2020/1148102020.

Sahuri, G., and Rosalina. 2020. Implementation of Deep Learning Methods in Detecting Disease on Chilli Leaf. Advances in Studies in Computation. 9(6): 10-15.

Deeba, K., and Amutha, B. 2020. ResNet - Deep Neural Network Architecture for Leaf Disease Classification. Microprocessors and Microsystems. Doi: https://doi.org/10.1016/j.micpro.2020.103364.

Francis, M., and Deisy, C. 2019. Disease Detection and Classification in Agricultural Plants Using Convolutional Neural Networks - A Visual Understanding. Signal Processing and Integrated Networks. Doi: https://doi.org/10.1109/spin.2019.8711701.

Alzubaidi, L., Zhang, J., Humaidi, A., J., Al-Dujaili, A., Duan, Y., Al-Shamma, O., Santamaría, J., Fadhel, M., A., Al-Amidie, M., and Farhan, L. 2021. Review of Deep Learning: Concepts, CNN Architectures, Challenges, Applications, Future Directions. Journal of Big Data. 8(1). Doi: https://doi.org/10.1186/s40537-021-00444-8.

Colaco, S., J., and Han, D., S. 2022. Deep Learning-based Facial Landmarks Localization using Compound Scaling. Access. IEEE. 10: 7653-7663. Doi: https://doi.org/10.1109/access.2022.3141791.

Jha, D., Gupta, V., Ward, L., Yang, Z., Wolverton, C., Foster, I., Liao, W. K., Choudhary, A., and Agrawal, A. 2021. Enabling Deeper Learning on Big Data for Materials Informatics Applications. Scientific Reports. 11(1). Doi: https://doi.org/10.1038/s41598-021-83193-1.

Kumar, V., Arora, H., Harsh, and Sisodia, J. 2020. ResNet-Based Approach for Detection and Classification of Plant Leaf Diseases. Electronics and Sustainable Communication Systems. Doi: https://doi.org/10.1109/icesc48915.2020.9155585.

Oyedotun, O., K., Ismaeil, K., A., and Aouada, D. 2021. Training Very Deep Neural Networks: Rethinking the Role of Skip Connections. Neurocomputing. 441: 105-117. Doi: https://doi.org/10.1016/j.neucom.2021.02.004

Jiang, X., Xiao, Z., Zhang, B., Zhen, X., Cao, X., Doermann, D., and Shao, L. 2019. Crowd Counting and Density Estimation by Trellis Encoder-Decoder Networks. Computer Vision and Pattern Recognition. 6133-6142.

Demir, F., Turkoglu, M., Aslan, M., and Sengur, A. 2020. A New Pyramidal Concatenated CNN Approach for Environmental Sound Classification. Applied Acoustics. DOI: https://doi.org/10.1016/j.apacoust.2020.107520

Acharya, A., Muvvala, A., Gawali, S., Dhopavkar, R., Kadam, R., and Harsola, A. 2020. Plant Disease Detection for Paddy Crop Using Ensemble of CNNs. Innovation in Technology.

Doi: https://doi.org/10.1109/inocon50539.2020.9298295.

Thambawita, V., Strümke, I., Hicks, S. A., Halvorsen, P., Parasa, S., and Riegler, M. A. 2021. Impact of Image Resolution on Deep Learning Performance in Endoscopy Image Classification: An Experimental Study Using a Large Dataset of Endoscopic Images. Diagnostics. 11(12): 2183. Doi: https://doi.org/10.3390/diagnostics11122183.

Tan, M., and Le, Q. 2019. Efficientnet: Rethinking Model Scaling for Convolutional Neural Networks. International Conference on Machine Learning. 6105-6114. Doi: https://doi.org/10.48550/arXiv.1905.11946.

Adedoja, A. O., Owolawi, P. A., Mapayi, T., and Tu, C. 2022. Intelligent Mobile Plant Disease Diagnostic System Using NASNet-Mobile Deep Learning. Computer Science. 1-16.

Setyanto, A., Kusrini, K., Sasongko, T. B., Permana, A. B., and Saputra, A. P. 2021. Efficient Deep Learning Architecture for Facemask Detection. Information and Communications Technology.

Doi: https://doi.org/10.1109/icoiact53268.2021.9564011.

Baron, G., and Stańczyk, U. 2021. Standard vs. Non-Standard Cross-Validation: Evaluation of Performance in a Space with Structured Distribution of Datapoints. Procedia Computer Science. 192: 1245-1254.

Doi: https://doi.org/10.1016/j.procs.2021.08.128.

Ghaffari, M., Monneret, A., Hammon, H., Post, C., Müller, U., Frieten, D., Gerbert, C., Dusel, G., and Koch, C. 2022. Deep Convolutional Neural Networks for the Detection of Diarrhea and Respiratory Disease in Preweaning Dairy Calves Using Data from Automated Milk Feeders. Dairy Science. 105(12): 9882-9895. Doi: https://doi.org/10.3168/jds.2021-21547.

Yu, X., Gong, Q., Chen, C., and Lu, L. 2022. Automatic Diagnosis of Soybean Leaf Disease by Transfer Learning. American Journal of Biochemistry and Biotechnology. 18(2): 252-260.

Doi: https://doi.org/10.3844/ajbbsp.2022.252.260