SavedAdd your journal

Journals / International Journal of Multidisciplinary Studies and Innovative Technologies / 2026 / Cilt: 6 Sayı: 1

Weeds Detection using Deep Learning Methods and Dataset Balancing

Fadıl Arıkan(EGE ÜNİVERSİTESİ, FEN BİLİMLERİ ENSTİTÜSÜ, BİLGİSAYAR MÜHENDİSLİĞİ (YL) (TEZLİ))0000-0002-0101-1524
Şebnem Bora(EGE ÜNİVERSİTESİ)0000-0003-0111-4635
Aybars Ugur(EGE ÜNİVERSİTESİ, MÜHENDİSLİK FAKÜLTESİ)0000-0003-3622-7672
Pages
19–22
Publication Date
2022-07-20
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

In this research, data augmentation was done using horizontal flip, rotation, width shift, height shift, and zoom.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Weeds have detrimental effects on agriculture and prove costly for farmers because they can quickly spread to fertile areas and reduce the fertility of the soil.
📊
Key Findings & Data:Architectures used in the research are as follows: ResNet152V2, DenseNet121, MobileNetV2, EfficientNetB1 and EfficientNetB7.
💡
Conclusion & Impact:In this research, data augmentation was done using horizontal flip, rotation, width shift, height shift, and zoom.
🔬Design:Araştırma Makalesi
📍Scope:Comprehensive Sample
⚙️Variables:deep learning · weed detection · EfficientNetB1

Abstract

Weeds have detrimental effects on agriculture and prove costly for farmers because they can quickly spread to fertile areas and reduce the fertility of the soil. Therefore, weed control is crucial for sustainable agriculture, and by detecting weeds and removing them from agricultural lands, we can transfer the limited resources we have to the plants to be grown, which would be a major step forward in sustainable agriculture. This article explores the feasibility of weed detection methods using deep learning architectures. Architectures used in the research are as follows: ResNet152V2, DenseNet121, MobileNetV2, EfficientNetB1 and EfficientNetB7. The F1-Score of EfficientNetB1 is 94.17\%, which is the highest score among those of all architectures. Among all architectures, EfficientNetB1 has the least number of parameters after MobileNetV2. In this research, data augmentation was done using horizontal flip, rotation, width shift, height shift, and zoom.

🔖

Cite This Article

Arıkan, F., Bora, Ş., Ugur, A. (2022). Weeds Detection using Deep Learning Methods and Dataset Balancing. International Journal of Multidisciplinary Studies and Innovative Technologies, Cilt: 6 Sayı: 1, 19–22. https://ajindex.com/articles/1496972

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (9)

  1. Ustuner, Tamer \& al Sakran, Muhammad \& Almhemed, Kamal. (2020). Herbisitlerin Ekosistemde Canlı Organizmalar Uzerine Etkisi Ve Alternatif Mucadele Yontemleri. International Journal of Scientific and Research Publications (IJSRP). 10. 633641.
  2. C. T. Selvi, R. S. Sankara Subramanian and R. Ramachandran, "Weed Detection in Agricultural fields using Deep Learning Process," 2021 7th International Conference on Advanced Computing and Communication Systems (ICACCS), 2021, pp. 1470-1473, doi: 10.1109/ICACCS51430.2021.9441683.
  3. M. N. Mowla and M. Gok, "Weeds Detection Networks," 2021 Innovations in Intelligent Systems and Applications Conference (ASYU), 2021, pp. 1-5, doi: 10.1109/ASYU52992.2021.9599046.
  4. Jabir, Brahim \& Noureddine, Falih \& Sarih, Asmaa \& TANNOUCHE, Adil. (2021). A Strategic Analytics Using Convolutional Neural Networks for Weed Identification in Sugar Beet Fields. Agris on-line Papers in Economics and Informatics. 13. 49-57. 10.7160/aol.2021.130104.
  5. K. Singh, R. Rawat, and A. Ashu, “Image Segmentation in Agriculture Crop and Weed Detection Using Image Processing and Deep Learning Techniques”, IJRESM, vol. 4, no. 5, pp. 235–238, Jun. 2021.
  6. C. A. Mamani Diaz, E. E. Medina Castaneda and C. A. Mugruza Vassallo, "Deep Learning for Plant Classification in Precision Agriculture," 2019 International Conference on Computer, Control, Informatics and its Applications (IC3INA), 2019, pp. 9-13, doi: 10.1109/IC3INA48034.2019.8949612.
  7. Giselsson, Thomas \& Jørgensen, Rasmus \& Jensen, Peter \& Dyrmann, Mads \& Midtiby, Henrik. (2017). A Public Image Database for Benchmark of Plant Seedling Classification Algorithms.
  8. Keras Applications. [Online]. Available: https://keras.io/api/applications/
  9. Balanced Data Coding. [Online]. Available: https://www.kaggle.com/gpiosenka/balance-data-with-augmentation-f1-score-93