SCN2Vit : Separable CNN-vision transformer with optimized transfer learning and YOLOv7 for bean leaf disease detection
*N. KumarCorresponding authornaresh@unizwa.edu.omDepartment of Mathematical and Physical SciencesCollege of Arts and SciencesUniversity of NizwaPC 616 Birkat Al Mouz, Nizwa, P.O. Box 33, Sultanate of OmanView full profile → , Mahendra Swainmr.mahendraswain@gmail.comPeerless Securities LimitedKolkata, West Bengal, 700069, IndiaView full profile → , Aftab Ahmedaftab.ahmad@unizwa.edu.omNatural and Medical Sciences Research CenterUniversity of NizwaPC 616 Birkat Al Mouz, Nizwa, P.O. Box 33, Sultanate of OmanView full profile →
* Corresponding author · click or hover a name for details
- Received:
- 01 Dec 2025
- Published Online:
- 30 Sep 2026
- Article type:
- Research Article
- Language:
- EN
- Article no.:
- JIOS-2428
- Pages:
- 3353–3369
Abstract
Ubiquitously promoting digital system emulates the human visual capabilities to get forward every manual step for fully automated system. Agriculture is one of the most necessary and fruitful domains for computer scientists to meet the satisfactory requirement of global and sustainable development. The meaning of sustainable development is pasteurized due to natural resources. The pollutant air, global warming badly impact of plants leaves. This article attempts to present a machine learning based leaf disease modeling framework. Plant diseases have contiguous impact and spread sharply; therefore, it is important to have an early detection of the disease. Considering the importance and badly impacting issues in leaf disease detection, we introduce Separable CNN Vision Transformer (SCN2Vit) model which utilizes a muti-headed vision transformer learnt from mobileNetv2 in transfer learning mode. The learnt feature to enhance the performance is trained from YOLOv7, a faster and real-time most accurate object detector. For optimizing the network Nesterov-Accelerated Adaptive Momentum (NADM) is used and ensured that SCN2Vit-YOLOv7 meets the challenges satisfactorily. The experiments were performed to test the model on publicly available collected from Makerere AI laboratory NaCRR institute.
Keywords
Subject Classifications
References
[1] E. Loizou, C. Karelakis, K. Galanopoulos, and K. Mattas, “The role of agriculture as a development tool for a regional economy,” Agricultural Systems, vol. 173, pp. 482–490 (2019).
[2] X. Diao, P. Hazell, and J. Thurlow, “The role of agriculture in african development,” World development, vol. 38, no. 10, pp. 1375– 1383 (2010).
[3] L. Selvam and P. Kavitha, “Classification of ladies finger plant leaf using deep learning,” Journal of Ambient Intelligence and Humanized Computing, pp. 1–9 (2020).
[4] A. Abade, P. A. Ferreira, and F. de Barros Vidal, “Plant diseases recognition on images using convolutional neural networks: A systematic review,” Computers and Electronics in Agriculture, vol. 185, p. 106125 (2021).
[5] R. Gajjar, N. Gajjar, V. J. Thakor, N. P. Patel, and S. Ruparelia, “Real-time detection and identification of plant leaf diseases using convolutional neural networks on an embedded platform,” The Visual Computer, vol. 38, no. 8, pp. 2923–2938 (2022).
[6] I. El Massi, Y. Es-saady, M. El Yassa, and D. Mammass, “Combi- nation of multiple classifiers for automatic recognition of diseases and damages on plant leaves,” Signal, Image and Video Processing, vol. 15, pp. 789–796 (2021).
[7] X. Huang, A. Chen, G. Zhou, X. Zhang, J. Wang, N. Peng, N. Yan, and C. Jiang, “Tomato leaf disease detection system based on fc- sndpn,” Multimedia Tools and Applications, pp. 1–24 (2022).
[8] R. Bora, D. Parasar, and S. Charhate, “A detection of tomato plant diseases using deep learning mndlnn classifier,” Signal, Image and Video Processing, pp. 1–9 (2023).
[9] N. Goyal, N. Kumar, and K. Gupta, “Lower-dimensional intrinsic structural representation of leaf images and plant recognition,” Signal, Image and Video Processing, pp. 1–8 (2022).
[10] M. Turkoglu, B. A. Yanikoglu, and D. Hanbay, “Plantdiseasenet: Convolutional neural network ensemble for plant disease and pest detection,” Signal, Image and Video Processing, vol. 16, no. 2, pp. 301–309 (2022).
[11] A. Beikmohammadi and K. Faez, “Leaf classification for plant recognition with deep transfer learning,” in 2018 4th Iranian Con- ference on Signal Processing and Intelligent Systems (ICSPIS). IEEE, pp. 21–26 (2018).
[12] A. P. Mullins and B. H. Arjmandi, “Health benefits of plant-based nutrition: focus on beans in cardiometabolic diseases,” Nutrients, vol. 13, no. 2, p. 519 (2021).
[13] K. K. Chakraborty, R. Mukherjee, C. Chakroborty, and K. Bora, “Automated recognition of optical image based potato leaf blight diseases using deep learning,” Physiological and Molecular Plant Pathology, vol. 117, p. 101781 (2022).
[14] S. R. Dubey and A. S. Jalal, “Apple disease classification using color, texture and shape features from images,” Signal, Image and Video Processing, vol. 10, pp. 819–826 (2016).
[15] P. K. Sethy, N. K. Barpanda, A. K. Rath, and S. K. Behera, “Deep feature based rice leaf disease identification using support vector machine,” Computers and Electronics in Agriculture, vol. 175, p. 105527 (2020).
[16] H.-T. Thai, K.-H. Le, and N. L.-T. Nguyen, “Formerleaf: An efficient vision transformer for cassava leaf disease detection,” Computers and Electronics in Agriculture, vol. 204, p. 107518 (2023).
[17] B. A. Kumar and M. Bansal, “Face mask detection on photo and real-time video images using caffe-mobilenetv2 transfer learning,” Applied Sciences, vol. 13, no. 2, p. 935 (2023).
[18] R. S. Alkhawaldeh, M. Alawida, N. F. F. Alshdaifat, W. Alma’aitah, and A. Almasri, “Ensemble deep transfer learning model for arabic (indian) handwritten digit recognition,” Neural Computing and Applications, vol. 34, no. 1, pp. 705–719 (2022).
[19] C.-Y. Wang, A. Bochkovskiy, and H.-Y. M. Liao, “Yolov7: Train- able bag-of-freebies sets new state-of-the-art for real-time object detectors,” arXiv preprint arXiv:2207.02696 (2022).
[20] A. Bochkovskiy, C.-Y. Wang, and H.-Y. M. Liao, “Yolov4: Op- timal speed and accuracy of object detection,” arXiv preprint arXiv:2004.10934 (2020).
[21] L. Li, S. Zhang, and B. Wang, “Plant disease detection and clas- sification by deep learning—a review,” IEEE Access, vol. 9, pp. 56683–56698 (2021).
[22] J. Liu and X. Wang, “Tomato diseases and pests detection based on improved yolo v3 convolutional neural network,” Frontiers in plant science, vol. 11, p. 898 (2020).
[23] R. Karthik, M. Hariharan, S. Anand, P. Mathikshara, A. Johnson, and R. Menaka, “Attention embedded residual cnn for disease detection in tomato leaves,” Applied Soft Computing, vol. 86, p. 105933 (2020).
[24] N. Krishnamoorthy, L. N. Prasad, C. P. Kumar, B. Subedi, H. B. Abraha, and V. Sathishkumar, “Rice leaf diseases prediction using deep neural networks with transfer learning,” Environmental Research, vol. 198, p. 111275 (2021).
[25] X. Nie, L. Wang, H. Ding, and M. Xu, “Strawberry verticillium wilt detection network based on multi-task learning and attention,” IEEE Access, vol. 7, pp. 170 003–170 011 (2019).
[26] R. Cristin, B. S. Kumar, C. Priya, and K. Karthick, “Deep neural network based rider-cuckoo search algorithm for plant disease detection,” Artificial intelligence review, vol. 53, no. 7, pp. 4993–5018 (2020).
[27] C. Bi, J. Wang, Y. Duan, B. Fu, J.-R. Kang, and Y. Shi, “Mobilenet based apple leaf diseases identification,” Mobile Networks and Applications, pp. 1–9 (2020).
[28] Y. Zhang, C. Song, and D. Zhang, “Deep learning-based object detection improvement for tomato disease,” IEEE Access, vol. 8, pp. 56 607–56 614 (2020).
[29] M. P. Mathew and T. Y. Mahesh, “Leaf-based disease detection in bell pepper plant using yolo v5,” Signal, Image and Video Processing, vol. 16, no. 3, pp. 841–847 (2022).
[30] R. Huang, J. Pedoeem, and C. Chen, “Yolo-lite: a real-time object detection algorithm optimized for non-gpu computers,” in 2018. IEEE International Conference on Big Data (Big Data). IEEE, pp. 2503–2510 (2018).
[31] Y. Tian, G. Yang, Z. Wang, H. Wang, E. Li, and Z. Liang, “Apple detection during different growth stages in orchards using the improved yolo-v3 model,” Computers and electronics in agriculture, vol. 157, pp. 417–426 (2019).
[32] N. Kumar, A. K. Jilani, P. Kumar, and A. Nikiforova, “Improved yolov3-tiny object detector with dilated cnn for drone-captured images,” in 2022 International Conference on Intelligent Data Science Technologies and Applications (IDSTA). IEEE, pp. 89–94 (2022).
[33] W. Bao, Z. Zhu, G. Hu, X. Zhou, D. Zhang, and X. Yang, “Uav remote sensing detection of tea leaf blight based on ddma-yolo,” Computers and Electronics in Agriculture, vol. 205, p. 107637 (2023).
[34] H. Zhao, J. An, M. Yu, D. Lv, K. Kuang, and T. Zhang, “Nesterov- accelerated adaptive momentum estimation-based wavefront dis- tortion correction algorithm,” Applied Optics, vol. 60, no. 24, pp. 7177–7185 (2021).
[35] J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You only look once: Unified, real-time object detection,” in Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 779– 788 (2016).
[36] W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C.-Y. Fu, and A. C. Berg, “Ssd: Single shot multibox detector,” in European conference on computer vision. Springer, pp. 21–37 (2016).
[37] A. Kumar and S. Srivastava, “Object detection system based on convolution neural networks using single shot multi-box detec- tor,” Procedia Computer Science, vol. 171, pp. 2610–2617 (2020).
[38] K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770–778 (2016).
[39] G. Huang, Z. Liu, L. Van Der Maaten, and K. Q. Weinberger, “Densely connected convolutional networks,” in Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 4700–4708 (2017).
[40] J. Redmon and A. Farhadi, “Yolo9000: better, faster, stronger,” in Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 7263–7271 (2017).
[41] J. Redmon and A. Farhadi, “YOLOv3: An incremental improvement,” arXiv preprint arXiv:1804.02767 (2018).
[42] T. Weyand, M. Andreetto, and H. Adam, “Mobilenets: Efficient convolutional neural networks for mobile vision applications,” arXiv preprint arXiv:1704.04861 (2017).
[43] M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen, “Mobilenetv2: Inverted residuals and linear bottlenecks,” in Pro- ceedings of the IEEE conference on computer vision and pattern recognition, pp. 4510–4520 (2018).
[44] M. Sozzi, S. Cantalamessa, A. Cogato, A. Kayad, and F. Marinello, “Automatic bunch detection in white grape varieties using yolov3, yolov4, and yolov5 deep learning algorithms,” Agronomy, vol. 12, no. 2, p. 319 (2022).
[45] A. Wong, M. Famuori, M. J. Shafiee, F. Li, B. Chwyl, and J. Chung, “Yolo nano: a highly compact you only look once convolutional neural network for object detection,” in 2019 Fifth Workshop on Energy Efficient Machine Learning and Cognitive Computing-NeurIPS Edition (EMC2-NIPS). IEEE, pp. 22–25 (2019).
[46] X. Zhu, S. Lyu, X. Wang, and Q. Zhao, “Tph-yolov5: Improved yolov5 based on transformer prediction head for object detection on drone-captured scenarios,” in Proceedings of the IEEE/CVF Inter- national Conference on Computer Vision, pp. 2778–2788 (2021).
[47] A. Kumar, A. Kalia, A. Sharma, and M. Kaushal, “A hybrid tiny yolo v4-spp module based improved face mask detection vision system,” Journal of Ambient Intelligence and Humanized Computing, pp. 1–14 (2021).
[48] A. S. Paymode and V. B. Malode, “Transfer learning for multi- crop leaf disease image classification using convolutional neural network vgg,” Artificial Intelligence in Agriculture, vol. 6, pp. 23–33 (2022).
[49] A. Arnab, M. Dehghani, G. Heigold, C. Sun, M. Lucˇic´, and C. Schmid, “Vivit: A video vision transformer,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 6836–6846 (2021).
[50] M. Kandemir, H. Zhao, X. Tang, and M. Karakoy, “Memory row reuse distance and its role in optimizing application performance,” in Proceedings of the 2015 ACM SIGMETRICS International Confer- ence on Measurement and Modeling of Computer Systems, pp. 137–149 (2015).
[51] H. Alshammari, K. Gasmi, I. Ben Ltaifa, M. Krichen, L. Ben Am- mar, and M. A. Mahmood, “Olive disease classification based on vision transformer and cnn models,” Computational Intelligence and Neuroscience, vol. 2022 (2022).
[52] X. Li and S. Li, “Transformer help cnn see better: A lightweight hybrid apple disease identification model based on transformers,” Agriculture, vol. 12, no. 6, p. 884 (2022).
[53] S. H. Abed, A. S. Al-Waisy, H. J. Mohammed, and S. Al-Fahdawi, “A modern deep learning framework in robot vision for automated bean leaves diseases detection,” International Journal of Intelligent Robotics and Applications, vol. 5, no. 2, pp. 235–251 (2021).
[54] J. Chen, H. Liu, Y. Zhang, D. Zhang, H. Ouyang, and X. Chen, “A multiscale lightweight and efficient model based on yolov7: Applied to citrus orchard,” Plants, vol. 11, no. 23, p. 3260 (2022).
[55] A. Krishnaswamy Rangarajan and R. Purushothaman, “Disease classification in eggplant using pre-trained vgg16 and msvm,” Scientific reports, vol. 10, no. 1, pp. 1–11 (2020).
[56] S. Mehta and M. Rastegari, “MobileViT: Light-weight, general-purpose, and mobile-friendly vision transformer,” in Proc. 2022 IEEE/CVF Conf. Comput. Vis. Pattern Recognit. Workshops (CVPRW), pp. 2120–2130 (2022).
[57] S. S. Kashyap, B. Unhelkar, S. S. Shankar, T. Chakrabarti, P. Chakrabarti, B. Sivaneasan, and M. Margala, “Optimized decision science approach for accurate detection of rice plant diseases,” J. Inf. Optim. Sci., vol. 45, no. 8, pp. 2081–2090 (2024), doi: 10.47974/JIOS-1652.
[58] S. Sachar and A. Kumar, “Deep learning for automatic identification of plants through leaf,” J. Inf. Optim. Sci., vol. 44, no. 4, pp. 709–716 (2023), doi: 10.47974/JIOS-1269.
