Deep Learning for Arecanut Maturity Assessment: A Comparative Analysis of Fine-Tuned CNN Models in RGB, Saturation, and Grayscale Domains
Keywords:
Arecanut, MobileNetV2, Classification, Convolution Neural Network, data-augmentation, fine-tuning and Transfer learning.Abstract
The classification of arecanut maturity is essential for agricultural practices, enabling precise harvesting and optimizing yield. This research explores a deep learning-based approach using transfer learning to classify arecanut maturity levels from images captured in field conditions. Leveraging four pre-trained convolutional neural network (CNN) models—MobileNetV2, InceptionV3, DenseNet-121, and VGG-16—the study analyses model performance across three distinct color spaces (RGB, Saturation, and Grayscale). Due to the limited dataset, data augmentation techniques such as rotations and flips were incorporated to expand the sample size and reduce overfitting. Fine-tuning was applied to the final layers of each model, adapting the networks to the task of arecanut classification. Results demonstrate that MobileNetV2 achieved the highest classification accuracy of 86.07% on RGB images, with accuracy metrics for each model showing that RGB space consistently outperformed Saturation and Grayscale spaces in this application. The findings suggest that combining fine-tuning and data augmentation optimizes model performance, providing a feasible solution for arecanut maturity classification in resource-limited agricultural settings.
Downloads
References
Naagarajan, R.; Meenakshi, R. Analysis of Areca Nut Production and Export in India. Int. J. Bus. Soc. Sci. 2016, 3, 67–81.
UAHS, S. Areca Referral Laboratory at UAHS, Shivamogga, 2021.
Dhanesha, R.; Shrinivasa, N.C.L. Segmentation of Arecanut Bunches Using YCgCr Color Model. In Proceedings of the 1st IEEE International Conference on Advances in Information Technology, 2019; pp. 50–53. https://doi.org/10.1007/978-1-7281-3241-9.
Danti, A.; S.M., 2012. Segmentation and Classification of Raw Arecanuts Based on Three-Sigma Control Limits. Elsevier Journal of C3IT-2012 4, 215–219. doi:10.1016/j.protcy.2012.05.032.
Siddesha, S., et al. Texture-Based Classification of Arecanut, in 2015 International Conference on Applied and Theoretical Computing and Communication Technology (iCATccT), pp. 688–692. doi:10.1109/ICATCCT.2015.7456971.
Dhanesha, R.; Shrinivasa, N.C.L. Segmentation of Arecanut Bunches Using HSV Color Model, in 2018 International Conference on Electrical, Electronics, Communication, Computer, and Optimization Techniques (ICEECCOT), pp. 37–41. doi:10.1109/ICEECCOT43722.2018.9001632.
Dhanesha, R.; Shrinivasa, N.C.L. Segmentation of Arecanut Bunches Using YCgCr Color Model, in 1st IEEE International Conference on Advances in Information Technology, 2019, pp. 50–53. doi:10.1007/978-1-7281-3241-9.
Siddesha, S., et al. Color Features and KNN in Classification of Raw Arecanut Images, in 2018 Second International Conference on Green Computing and Internet of Things (ICGCIoT), pp. 504–509. doi:10.1109/ICGCIoT.2018.8753075.
Sanghvi, K.; Ramesha, K.; Gupta, P. A Survey on Image Classification Techniques. Int. J. Comput. Appl. 2017, 112(1), 16–22.
Mathworks. Review of Image Classification Algorithms Based on Convolutional Neural Networks. September 24, 2020. https://www.mdpi.com/2072-4292/13/22/4712.
Russakovsky, O.; Deng, J., et al. Imagenet Large Scale Visual Recognition Challenge. Int. J. Comput. Vision 2015, 115, 211–252.
Kamilaris, A.; Prenafeta-Boldú, F.X. Deep Learning in Agriculture: A Survey. Computers and Electronics in Agriculture 2018.
Lu, Y.; Yi, S.; Zeng, N.; Liu, Y.; Zhang, Y. Identification of Rice Diseases Using Deep Convolutional Neural Networks. Neurocomputing 2017.
Hussain, M.; et al. A Study on CNN Transfer Learning for Image Classification, in UK Workshop on Computational Intelligence, Springer, Germany, 2018; pp. 191–202. doi:10.1007/978-3-319-97982-3_16.
Sandler, M.; Howard, A.; Zhu, M.; Zhmoginov, A.; Chen, L.-C. MobileNetV2: Inverted Residuals and Linear Bottlenecks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2018.
Too, E.C.; Yujian, L.; Njuki, S.; Yingchun, L. A Comparative Study of Fine-Tuning Deep Learning Models for Plant Disease Identification. Computers and Electronics in Agriculture 2019.
Huang, G.; Liu, Z.; Van Der Maaten, L.; Weinberger, K.Q. Densely Connected Convolutional Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017.
Yalcin, H.; Razavi, S. Plant Classification Using Convolutional Neural Networks. Eur. J. Sci. Technol. 2016.
Szegedy, C.; Vanhoucke, V.; Ioffe, S.; Shlens, J.; Wojna, Z. Rethinking the Inception Architecture for Computer Vision. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2016.
Mohanty, S.P.; Hughes, D.P.; Salathé, M. Using Deep Learning for Image-Based Plant Disease Detection. Front. Plant Sci. 2016.
Simonyan, K.; Zisserman, A. Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv Preprint arXiv:1409.1556 2014.
Davangere University. Arecanut Database. Available online: http://davangereuniversity.ac.in/arecanut-database/.
Gonzalez, R.C.; Woods, R.E. Digital Image Processing, 2nd ed.; Prentice Hall: Upper Saddle River, NJ, 2002.
Cheng, H.D.; Jiang, X.H.; Sun, Y.; Wang, J. Color Image Segmentation: Advances and Prospects. Pattern Recognit. 2001, 34(12), 2259–2281.
Fairchild, M. Color Appearance Models; Reading: Addison-Wesley, 1998.
LeCun, Y.; Bengio, Y.; Hinton, G. Deep Learning. Nature 2015, 521(7553), 436–444.
Kading, C.R.E. Fine-Tuning Deep Neural Networks in Continuous Learning Scenarios. In Chen CS., Lu J., Ma KK. (Eds.) Computer Vision – ACCV 2016 Workshops. Lecture Notes in Computer Science, 2017.
Perez, L.; Wang, J. The Effectiveness of Data Augmentation in Image Classification Using Deep Learning. arXiv:1712.04621 2017.
Google Research. Colaboratory. Available online: https://colab.research.google.com/.
Abadi, M.; Barham, P.; Brevdo, E.; et al. TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems. arXiv Preprint arXiv:1605.07603 2016.
Chollet, F. Keras. 2015. Available online: https://keras.io/.
Kingma, D.P.; Ba, J. Adam: A Method for Stochastic Optimization. arXiv Preprint arXiv:1412.6980 2015.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Umesha D. K., Venkata Krishna J, Dhanesha R, Gurudeva Shastri Hiremath, Narendra Kumar S
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.
