Advancements in Weed Detection with Deep Learning Models and Image Augmentation Techniques
Keywords:
Deep learning, Computer vision, Tensorflow, Keras, ReLU, Stochastic Gradient Descent, vgg, transformersAbstract
Deep-Learning is one of the potent technique for automating weed detection procedures. This study offers a thorough investigation of deep learning methods for weed identification, emphasizing training-models such as Convolutional-Neural Networks (CNN), Autoencoders & Vision-Transformers. Specifically, CNNs are skilled at identifying hierarchical complex features from high dimensional images, while Autoencoders facilitate unsupervised feature learning, and Vision transformers which uses the power Attention Neural Networks enable selective focus on relevant regions in images. We review recent developments, difficulties, and potential paths in utilizing these deep learning models for weed detection, highlighting how they could transform farming methods by facilitating accurate and timely weed management strategies. Dataset contain images of carrot and weed which contain 250 training images out of which 130 carrot plant images and 120 weed image. There is 70% testing images with RGB range of 0 to 255. As we have only small dataset to ensure the model's resilience various argumentation where applied like flipping – horizontal/vertical, Magnified Range, brightness, height shift range and width shift range.
Downloads
Metrics
References
J. Sangeetha a, Priya Govindarajan b, “Prediction of agricultural waste compost maturity using fast regions with convolutional neural network(R-CNN)”, Materialstoday Proceedings, DOI: https://doi.org/10.1016/j.matpr.2023.01.112, Published: 2023.
[2] Nanyang Zhu, Xu Liu, Ziqian Liu, Kai Hu, Yingkuan Wang, Jinglu Tan, Min Huang, Qibing Zhu, Xunsheng Ji, Yongnian Jiang, Ya Guo, “Deep learning for smart agriculture: Concepts, tools, applications, and opportunities”,International Journal of Agricultural and Biological Engineering, Vol 11, No 4 (2018), DOI: 10.25165/j.ijabe.20181104.4475, Published on: 2018.
[3] Muhammad Hammad Saleem 1,Johan Potgieter 2 andKhalid Mahmood Arif 1, Plant Disease Detection and Classification by Deep Learning”, Plants 2019, 8(11), 468; https://doi.org/10.3390/plants8110468, Published: 31 October 2019
S. Kavitha, T. Satish Kumar, E. Naresh, Vijay H. Kalmani, Kalyan Devappa Bamane & Piyush Kumar Pareek, “Medicinal Plant Identification in Real-Time Using Deep Learning Model”, SN COMPUT. SCI, DOI: https://doi.org/10.1007/s42979-023-02398-5, Volume 5, article number 73, Published: 07 December 2023.
Jun Liu & Xuewei Wang, “Plant diseases and pests detection based on deep learning: a review”, Plant Method 17,Article number:22, DOI: https://doi.org/10.1186/s13007-021-00722-9, Published: 2021.
Alvaro Fuentes, Sook Yoon & Dong Sun Park, “Deep Learning-Based Techniques for Plant Diseases Recognition in Real-Field Scenarios”, Springer , Volume 12002, ISBN : 978-3-030-40604-2, Published on: 06 February 2020
Sunil G C a, Yu Zhang a, Cengiz Koparan a, Mohammed Raju Ahmed a, Kirk Howatt b, Xin Sun a, ”Weed and crop species classification using computer vision and deep learning technologies in greenhouse conditions”, Journal of Agriculture and Food Research, Volume 9, DOI:10.1016/j.jafr.2022.100325, Published on: September 2022
Senthil Kumar Swami Durai a, Mary Divya Shamili b, “Smart farming using Machine Learning and Deep Learning techniques”,Decision Analytics Journal,Volume 3, DOI: https://doi.org/10.1016/j.dajour.2022.100041, Published on: June 2022.
Niranjan C Kundur; P B Mallikarjuna, “Pest Detection and Recognition: An approach using Deep Learning Technique”, 2022 Fourth International Conference on Cognitive Computing and Information Processing (CCIP), pp. 1-6, DOI: 10.1109/CCIP57447.2022.10058692, Published: 2022
Seyit Kerimkhulle; Zhandos Kerimkulov; Dias Bakhtiyarov; Nazerke Turtayeva; Jong Kim, ”In-Field Crop-Weed Classification Using Remote Sensing and Neural Network”, pp. 1-6, DOI: 10.1109/SIST50301.2021.9465970, Published in 2021.
/
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
You are free to:
- Share — copy and redistribute the material in any medium or format
- Adapt — remix, transform, and build upon the material for any purpose, even commercially.
Terms:
- Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
