Identification of fungi infecting Zea mays leaves and sub-classifying them to have correct course management in the earlier stages is lucrative. To develop a nondestructive and low-cost classification model of corn leaves infected by Setosphaeria turcica (ST), Cercospora zeae-maydis (CZM), and Puccinia sorghi (PS) fungi using image filtering and transfer learning model. Corn leaf images were categorized based on fungal-infection and stored in an image library. All images were then processed to show different intensities and then utilized to filter the images. An original RGB-based CNN model has been compared with selected pre-trained models of VGG16 and EfficientNet-b0 with inputs of both unfiltered and filtered RGB images. Results showed that the EfficientNet-b0 with filtered images model (fMaize) exhibited the highest accuracy of 97.63%, sensitivity of 97.99%, specificity of 97.38, quality index of 97.68%, and F-score of 96.48%. Consequently, the experimental results revealed that deep transfer learning models fed with filtered images produced higher accuracy than models that simply employed RGB images. Thus, transfer learning was proven to be a valuable tool in enhancing CNN image classification accuracy.

1. [1] J. D. Alejandrino, “Remote Monitoring System for Outland Precision Farming,” Master’s Thesis, De La Salle University, 2021.
2. [2] M. L. Russo et al., “Effect of entomopathogenic fungi introduced as corn endophytes on the development, reproduction, and food preference of the invasive fall armyworm Spodoptera frugiperda,” J. of Pest Science, Vol.94, No.3, pp. 859-870, doi: 10.1007/s10340-020-01302-x, 2021.
3. [3] G. P. Munkvold et al., “Chapter 9 – Mycotoxins in corn: Occurrence, impacts, and management,” S. O. Serna-Saldivar (Ed.), “Corn: Chemistry and Technology, 3rd Edition,” pp. 235-287, Elsevier, doi: 10.1016/B978-0-12-811971-6.00009-7, 2018.
4. [4] M. Noor et al., “Heritability and correlation analysis of morphological and yield traits in Maize,” J. Plant Biol. Crop Res., No.2, pp. 1008-1015, 2018.
5. [5] J. D. Alejandrino et al., “Cluster-Based Network for Improved Internet Resilience in Outland Agriculture,” IEEE 9th Region 10 Humanitarian Technology Conf. (R10-HTC), doi: 10.1109/R10-HTC53172.2021.9641523, 2021.
6. [6] I. Egusquiza et al., “Analysis of Few-Shot Techniques for Fungal Plant Disease Classification and Evaluation of Clustering Capabilities Over Real Datasets,” Frontiers in Plant Science, Vol.13, Article No.813237, doi: 10.3389/fpls.2022.813237, 2022.
7. [7] Y. Meng et al., “Novel factors contributing to fungal pathogenicity at early stages of Setosphaeria turcica infection,” Molecular Plant Pathology, Vol.23, No.1, pp. 32-44, doi: 10.1111/mpp.13140, 2022.
8. [8] D. L. Neves and C. A. Bradley, “Baseline sensitivity of Cercospora zeae-maydis to pydiflumetofen, a new succinate dehydrogenase inhibitor fungicide,” Crop Protection, Vol.119, pp. 177-179, doi: 10.1016/j.cropro.2019.01.021, 2019.
9. [9] S. Debnath, S. Chhetri, and S. Biswas, “Southern Rust Disease of Corn – A Review,” Int. J. of Current Microbiology and Applied Sciences, Vol.8, No.11, pp. 855-862, doi: 10.20546/ijcmas.2019.811.101, 2019.
10. [10] S. Kaur, S. Pandey, and S. Goel, “Plants Disease Identification and Classification Through Leaf Images: A Survey,” Archives of Computational Methods in Engineering, Vol.26, No.2, pp. 507-530, doi: 10.1007/s11831-018-9255-6, 2019.
11. [11] D. Singh, N. Jain, P. Jain et al., “PlantDoc: A dataset for visual plant disease detection,” Proc. of the 7th ACM IKDD CoDS and 25th COMAD, pp. 249-253, doi: 10.1145/3371158.3371196, 2020.
12. [12] J. D. Alejandrino et al., “Application-Based Cluster and Connectivity-Specific Routing Protocol for Smart Monitoring System,” IEEE 12th Int. Conf. on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment, and Management (HNICEM), doi: 10.1109/HNICEM51456.2020.9400107, 2020.
13. [13] M. Gandhi, J. Kamdar, and M. Shah, “Preprocessing of Non-Symmetrical Images for Edge Detection,” Augmented Human Research, Vol.5, Article No.10, doi: 10.1007/s41133-019-0030-5, 2020.
14. [14] R. S. Concepcion II et al., “Lettuce growth stage identification based on phytomorphological variations using coupled color superpixels and multifold watershed transformation,” Int. J. of Advances in Intelligent Informatics, Vol.6, No.3, pp. 261-277, doi: 10.26555/ijain.v6i3.435, 2020.
15. [15] L. Li et al., “A Large-Scale Database and a CNN Model for Attention-Based Glaucoma Detection,” IEEE Trans. on Medical Imaging, Vol.39, No.2, pp. 413-424, doi: 10.1109/TMI.2019.2927226, 2020.
16. [16] G. Vrbančič and V. Podgorelec, “Transfer learning with adaptive fine-tuning,” IEEE Access, Vol.8, pp. 196197-196211, doi: 10.1109/ACCESS.2020.3034343, 2020.
17. [17] J. D. Alejandrino et al., “Utilization of Self-Organizing Maps for Map Depiction of Multipath Clusters,” P. Vasant, I. Zelinka, and G. W. Weber (Eds.), Intelligent Computing & Optimization (ICO 2021), Lecture Notes in Networks and Systems, Vol.371, pp. 417-426, doi: 10.1007/978-3-030-93247-3_41, 2022.