Disease Detection In Fruit Using Image Processing and Machine Learning

Abstract

Fruit diseases significantly affect agricultural productivity and food quality, leading to economic losses for farmers. Early detection and proper diagnosis of fruit diseases are essential to ensure healthy crop production and prevent the spread of infections. This study presents a Multi-Fruits Disease Detection System using Machine Learning that automatically identifies diseases from fruit images using deep learning techniques. The proposed system utilizes a Convolutional Neural Network (CNN) based on the MobileNetV2 architecture with transfer learning to accurately classify different fruit diseases. The system is designed with a user-friendly web interface developed using the Flask framework, allowing users to upload fruit images for analysis. The uploaded images are preprocessed and resized before being passed to the MobileNetV2 model, which extracts relevant features through depthwise separable convolutions. A custom classification head consisting of global average pooling, dropout, and dense layers with Softmax activation is used to classify the detected disease. The system then predicts the disease category and provides suggested remedies through the interface. The proposed model offers an efficient and lightweight solution for real-time fruit disease detection, making it suitable for agricultural applications. By automating the disease identification process, the system helps farmers and agricultural experts take timely preventive measures, improving crop quality and reducing potential losses. The integration of machine learning with a web-based interface enhances accessibility and usability, making the system practical for modern smart farming environments.

Introduction

Agriculture plays a vital role in global food production and economic development, and fruits are an important source of essential nutrients such as vitamins, minerals, and antioxidants. However, fruit crops are frequently affected by diseases caused by fungi, bacteria, viruses, and environmental conditions. These diseases reduce crop quality and yield, leading to significant economic losses for farmers. Traditional methods of disease detection rely on manual inspection by farmers or agricultural experts, which is time-consuming, requires specialized knowledge, and may result in inaccurate diagnosis when different diseases show similar symptoms.

Recent advancements in artificial intelligence, computer vision, and machine learning have enabled the development of automated systems that can detect fruit diseases using digital images. In particular, deep learning techniques such as Convolutional Neural Networks (CNNs) are highly effective for image classification because they can automatically identify important visual features such as color patterns, textures, and spots on fruit surfaces. These technologies help detect diseases at an early stage, allowing farmers to take preventive actions and improve crop productivity.

To address the limitations of large dataset requirements and high computational cost, transfer learning is used with pre-trained models. One efficient architecture is MobileNetV2, a lightweight deep learning model that uses depthwise separable convolutions to reduce computational complexity while maintaining high accuracy. This makes it suitable for real-time agricultural applications and systems with limited processing power.

The proposed Multi-Fruits Disease Detection System uses a CNN model based on MobileNetV2 with transfer learning to automatically identify diseases from fruit images. The system also includes a web-based interface (using Flask) that allows users to upload fruit images and receive instant disease predictions along with suggested remedies.

The main objectives of the system are to:

• Automatically detect and classify diseases in different fruits.

• Use image processing and deep learning for accurate disease identification.

• Provide a user-friendly platform where users can upload fruit images easily.

• Suggest preventive measures to help farmers manage crop health.

The system workflow includes dataset collection, image preprocessing, feature extraction, disease classification, and result display. Images are collected from agricultural datasets and resized to a standard size before being processed by the deep learning model.

Overall, the proposed system aims to support smart agriculture and precision farming by providing a fast, accurate, and automated method for fruit disease detection. This technology can help farmers monitor crop health, reduce crop losses, and improve agricultural productivity.

Conclusion

The Multi-Fruits Disease Detection System using Machine Learning provides an effective and intelligent solution for identifying fruit diseases automatically through image analysis. The proposed system utilizes a Convolutional Neural Network based on the MobileNetV2 architecture with transfer learning to accurately classify diseases present in fruit images. By combining image preprocessing, feature extraction, and deep learning classification techniques, the system is able to detect disease symptoms such as spots, discoloration, and texture variations on fruit surfaces. The integration of a web-based interface developed using the Flask framework allows users to easily upload fruit images and obtain disease predictions along with suggested remedies. The developed system helps reduce the dependency on manual inspection and expert diagnosis, which are often time-consuming and not always accessible to farmers. By providing quick and reliable disease detection, the system enables farmers and agricultural professionals to take timely preventive actions, thereby minimizing crop damage and improving overall productivity. The proposed approach demonstrates how machine learning and deep learning technologies can be effectively applied in agriculture to support smart farming practices. Overall, the system contributes to improved crop health monitoring and represents a practical step toward the development of intelligent agricultural decision-support systems.

References

[1] S. P. Mohanty, D. P. Hughes, and M. Salathé, “Using deep learning for image-based plant disease detection,” Frontiers in Plant Science, 2016. [2] K. P. Ferentinos, “Deep learning models for plant disease detection and diagnosis,” Computers and Electronics in Agriculture, 2018. [3] M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L. Chen, “MobileNetV2: Inverted residuals and linear bottlenecks,” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018. [4] E. C. Too, L. Yujian, S. Njuki, and L. Yingchun, “A comparative study of fine-tuning deep learning models for plant disease identification,” Computers and Electronics in Agriculture, 2019. [5] S. Sladojevic, M. Arsenovic, A. Anderla, D. Culibrk, and D. Stefanovic, “Deep neural networks based recognition of plant diseases by leaf image classification,” Computational Intelligence and Neuroscience, 2016. [6] Kamilaris and F. X. Prenafeta-Boldú, “Deep learning in agriculture: A survey,” Computers and Electronics in Agriculture, 2018. [7] J. Amara, B. Bouaziz, and A. Algergawy, “A deep learning-based approach for banana leaf disease classification,” Lecture Notes in Informatics, 2017. [8] P. P. Revathi and M. Hemalatha, “Classification of cotton leaf spot diseases using image processing edge detection techniques,” International Journal of Computer Science and Engineering, 2012. [9] S. P. Pujari, R. Yakkundimath, and A. S. Byadgi, “Image processing based detection of fungal diseases in plants,” Procedia Computer Science, 2016. [10] H. Durmu?, E. O. Güne?, and M. K?rc?, “Disease detection on the leaves of the tomato plants by using deep learning,” IEEE International Conference on Agro-Geoinformatics, 2017. [11] R. Brahimi, K. Boukhalfa, and A. Moussaoui, “Deep learning for tomato diseases classification and symptoms visualization,” Applied Artificial Intelligence, 2017. [12] S. Zhang, W. Huang, and C. Zhang, “Three-channel convolutional neural networks for vegetable leaf disease recognition,” Cognitive Systems Research, 2019. [13] Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, 2015. [14] Krizhevsky, I. Sutskever, and G. Hinton, “ImageNet classification with deep convolutional neural networks,” Advances in Neural Information Processing Systems, 2012. [15] K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” International Conference on Learning Representations, 2015. [16] Szegedy et al., “Going deeper with convolutions,” IEEE Conference on Computer Vision and Pattern Recognition, 2015. [17] K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” IEEE Conference on Computer Vision and Pattern Recognition, 2016. [18] G. Huang, Z. Liu, L. Van Der Maaten, and K. Weinberger, “Densely connected convolutional networks,” IEEE Conference on Computer Vision and Pattern Recognition, 2017. [19] T. Chen and C. Guestrin, “XGBoost: A scalable tree boosting system,” ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016. [20] J. Schmidhuber, “Deep learning in neural networks: An overview,” Neural Networks, 2015. [21] L. Breiman, “Random forests,” Machine Learning Journal, 2001. [22] R. Girshick, “Fast R-CNN,” IEEE International Conference on Computer Vision, 2015. [23] J. Redmon and A. Farhadi, “YOLOv3: An incremental improvement,” Computer Vision and Pattern Recognition Workshop, 2018. [24] W. Liu et al., “SSD: Single shot multibox detector,” European Conference on Computer Vision, 2016. [25] Goodfellow, Y. Bengio, and A. Courville, Deep Learning, MIT Press, 2016. [26] P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” International Conference on Learning Representations, 2015. [27] F. Chollet, “Xception: Deep learning with depthwise separable convolutions,” IEEE Conference on Computer Vision and Pattern Recognition, 2017. [28] Howard et al., “MobileNets: Efficient convolutional neural networks for mobile vision applications,” arXiv preprint arXiv:1704.04861, 2017. [29] M. Everingham et al., “The Pascal visual object classes challenge,” International Journal of Computer Vision, 2010. [30] O. Russakovsky et al., “ImageNet large scale visual recognition challenge,” International Journal of Computer Vision, 2015.

Copyright

Copyright © 2026 Pranjali Santosh Pingat, Saniya Rahul Labade, Harshada Sahebrao Lende, Prof. Kedar A. L.. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.