Automated Weed Detection for Sustainable Agriculture Using CNN and Image Processing
Keywords:
Smart Weed Control, Convolutional Neural Network, Image Processing, IoT, Raspberry Pi, Watershed Segmentation, Machine Learning, Agriculture TechnologyAbstract
Farming serves as the primary source of income for more than half of the Indian population. One of the major challenges in agriculture is the effective control of weeds in plantation crops. Currently, weeds are managed through manual labour or by applying herbicides across the entire field. This method is inefficient, as it leads to environmental pollution and poses health risks to humans. To mitigate these issues, a smart weed control system using Convolutional Neural Networks (CNN), image processing, and IoT is proposed. The CNN model is trained using a large dataset of weed and crop images. This trained model is deployed on a Raspberry Pi for real-time weed detection. The captured images are segmented using the Watershed Segmentation Algorithm, and each segment is classified as weed or crop using the CNN model. The detected weed regions are highlighted and sent to farmers via email for further action. The system was evaluated using 250 images and achieved an average accuracy of 85%, a false ratio of 7%, and a false acceptance ratio of 2.6%.
Downloads
References
Ghazali, K. H., Mustafa, M. M., & Hussain, A. (2008). Machine vision system for automatic weeding strategy in oil palm plantation using image filtering technique. American-Eurasian Journal of Agriculture & Environmental Science, 3(3).
Kargar B, A. H., & Shirzadifar, A. M. (2013). Automatic weed detection system and smart herbicide sprayer robot for corn fields. IEEE International Conference on Robotics and Mechatronics, 468–473.
Siddiqi, M. H., Ahmad, I., & Sulaiman, S. B. (2009). Weed recognition based on erosion and dilation segmentation algorithm. International Conference on Education Technology and Computer, Singapore.
Ishak, A. J., Mokri, S. S., Mustafa, M. M., & Hussain, A. (2007). Weed detection utilizing quadratic polynomial and ROI techniques. 5th Student Conference on Research and Development, Malaysia.
Burgos-Artizzu, X. P., Ribeiro, A., Guijarro, M., & Pajares, G. (2010). Real-time image processing for crop/weed discrimination in maize fields. Elsevier.
Deshmukh, A. G., & Kulkarni, V. A. (2013). Advanced robotic weeding system. Transactions on Electrical and Electronics Engineering, 1(3).
Liu, C., Wang, M., & Zhou, J. (2008). Co-ordinating control for an agricultural vehicle with individual wheel speeds and steering angles. IEEE Control Systems Magazine.
Pota, H., Eaton, R., Katupitiya, J., & Pathirana, S. D. (2007). Agricultural robotics: A streamlined approach to realization of autonomous farming. 2nd International Conference on Industrial and Information System, IEEE.
Tejeda, A. J. I., & Castro, R. C. (2019). Algorithm of weed detection in crops by computational vision. International Conference on Electronics, Communications and Computers, IEEE.
Umamaheswari, S., Arjun, R., & Meganathan, D. (2018). Weed detection in farm crops using parallel image processing. International Conference on Information and Communication Technology (CICT).
Sandino, J., & Gonzalez, F. (2018). A novel approach for invasive weeds and vegetation surveys using UAS and artificial intelligence. 23rd International Conference on Methods & Models in Automation & Robotics (MMAR).
Wafy, M., Ibrahim, H., & Kamel, E. (2013). Identification of weed seeds species in mixed sample with wheat grains using SIFT algorithm. 9th International Computer Engineering Conference (ICENCO).
Bah, M. D., Hafiane, A., & Canals, R. (2017). Weeds detection in UAV imagery using SLIC and the hough transform. Seventh International Conference on Image Processing Theory, Tools and Applications (IPTA).
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
