Modify Resnet 101: Quality Evaluation of Fruit Recognition and Classification based on Deep Learning
Keywords:
Deep Learning (DL), Convolutional neural network (CNN), Recognition, Classification, ResNet101Abstract
Recognizing and categorizing fruits is a unique challenge in the field of computer vision due to the wide variation in their appearance, shape, and texture. In this research, the effectiveness of an enhanced ResNet-101 deep convolutional neural network (CNN) architecture to achieve higher accuracy in fruit recognition and classification is explored compared to other deep learning (DL) models. The improved ResNet-101 model leverages its depth, skip connections, and pre-trained weights to capture intricate and distinctive features, making it particularly adept at handling complex visual tasks. In our experiments, it was observed that this enhanced ResNet-101 model outperforms several other cutting-edge DL models when applied to a diverse and demanding fruit classification dataset. The model's robustness in dealing with a wide range of fruits, including those with subtle variations and occlusions, is highlighted in our study. Furthermore, the significance of tuning hyperparameters, applying data preprocessing techniques, and utilizing data augmentation strategies is delved into. These aspects are deemed crucial for optimizing the performance of the enhanced ResNet-101 model. By striking the right balance between model complexity and dataset size, the issue of overfitting is addressed while still achieving exceptional accuracy. In essence, the presented model showcases enhanced accuracy performance within 15 epochs, achieving an impressive 99.97% accuracy across a dataset comprising 40 different types of fruits. The findings underscore the superior performance of the proposed model, surpassing the efficacy of several commonly employed methods in current use. This model's effectiveness and robustness for fruit recognition and classification are demonstrated. By reducing the number of trainable parameters by 81%, the overall complexity of the model is decreased. Faster training times, fewer computational resources required, potentially improved generalization, and a reduced likelihood of overfitting can be achieved through this reduction in complexity.
Downloads
References
Pham, T. T., Nguyen, L. L. P., Dam, M. S., & Baranyai, L. (2023). Application of Edible Coating in Extension of Fruit Shelf Life. AgriEngineering, 5(1), 520-536.
Bùi, V. P. (2023). Fruit type and weight recognition for payment purposes using computer vision (Doctoral dissertation, FPTU Hà Nội).
Sugandi, B., Wahyu, R., Apriliana, S., & Putri, F. R. (2023). Fruit Recognition and Weight Scale Estimation Based on Visual Sensing. International ABEC, 234-241.
Indira, D. N. V. S. L. S., Goddu, J., Indraja, B., Challa, V. M. L., & Manasa, B. (2023). A review on fruit recognition and feature evaluation using CNN. Materials Today: Proceedings, 80, 3438-3443.
Lin, M. (2023). Fruit Classification based on ResNet and Attention Mechanism. Highlights in Science, Engineering and Technology, 34, 163-167.
Wangchuk, K., Dorji, T., Dhungyel, P. R., Galey, P., & Chhetri, M. Fruits and Vegetables Recognition System in Dzongkha Using Visual Geometry Group Network.
Kumari, R. S. S., & Gomathy, V. (2023). Fruit shop tool: Fruit classification and recognition using deep learning. Agricultural Engineering International: CIGR Journal, 25(2).
Hussain, D., Hussain, I., Ismail, M., Alabrah, A., Ullah, S. S., & Alaghbari, H. M. (2022). A simple and efficient deep learning-based framework for automatic fruit recognition. Computational Intelligence and Neuroscience, 2022.
Wang, J. J. (2022). Recognition system for fruit classification based on 8-layer convolutional neural network. EAI Endorsed Transactions on e-Learning, 7(23).
Yu, F., Lu, T., & Xue, C. (2023). Deep Learning-Based Intelligent Apple Variety Classification System and Model Interpretability Analysis. Foods, 12(4), 885.
Aherwadi, N., Mittal, U., Singla, J., Jhanjhi, N. Z., Yassine, A., & Hossain, M. S. (2022). Prediction of fruit maturity, quality, and its life using deep learning algorithms. Electronics, 11(24), 4100.
Hassan, N. M. H., Elshoky, B., Hassan, N. M. H., Elshoky, B. R. G., & Mabrouk, A. M. (2023). Quality of performance evaluation of ten machine learning algorithms in classifying thirteen types of apple fruits. Indones. J. Electr. Eng. Comput. Sci, 30, 102-109.
Gill, H. S., Murugesan, G., Mehbodniya, A., Sajja, G. S., Gupta, G., & Bhatt, A. (2023). Fruit type classification using deep learning and feature fusion. Computers and Electronics in Agriculture, 211, 107990.
Tu, Bing, et al. "Feature extraction via joint adaptive structure density for hyperspectral imagery classification." IEEE Transactions on Instrumentation and Measurement 70 (2021): 1-16.
Mutlag, W. K., Ali, S. K., Aydam, Z. M., & Taher, B. H. (2020, July). Feature extraction methods: a review. In Journal of Physics: Conference Series (Vol. 1591, No. 1, p. 012028). IOP Publishing.
Nixon, M., & Aguado, A. (2019). Feature extraction and image processing for computer vision. Academic press.
Dhiman, G., Kumar, A. V., Nirmalan, R., Sujitha, S., Srihari, K., Yuvaraj, N., ... & Raja, R. A. (2023). Multi-modal active learning with deep reinforcement learning for target feature extraction in multi-media image processing applications. Multimedia Tools and Applications, 82(4), 5343-5367.
Ekramirad, N., Khaled, A. Y., Donohue, K. D., Villanueva, R. T., & Adedeji, A. A. (2023). Classification of Codling Moth-Infested Apples Using Sensor Data Fusion of Acoustic and Hyperspectral Features Coupled with Machine Learning. Agriculture, 13(4), 839.
Gao, G., Xu, Z., Li, J., Yang, J., Zeng, T., & Qi, G. J. (2023). Ctcnet: A cnn-transformer cooperation network for face image super-resolution. IEEE Transactions on Image Processing, 32, 1978-1991.
Hamid, N. N. A. A., Razali, R. A., & Ibrahim, Z. (2019). Comparing bags of features, conventional convolutional neural network and AlexNet for fruit recognition. Indonesian Journal of Electrical Engineering and Computer Science, 14(1), 333.
Iandola, F. N., Han, S., Moskewicz, M. W., Ashraf, K., Dally, W. J., & Keutzer, K. (2016). SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and< 0.5 MB model size. arXiv preprint arXiv:1602.07360.
Zhu, L., Li, Z., Li, C., Wu, J., & Yue, J. (2018). High performance vegetable classification from images based on alexnet deep learning model. International Journal of Agricultural and Biological Engineering, 11(4), 217-223.
Loey, M., Manogaran, G., Taha, M. H. N., & Khalifa, N. E. M. (2021). Fighting against COVID-19: A novel deep learning model based on YOLO-v2 with ResNet-50 for medical face mask detection. Sustainable cities and society, 65, 102600.
Alzamily, J. Y. I., Ariffin, S. B., & Abu-Naser, S. S. (2022). Classification of Encrypted Images Using Deep Learning–Resnet50. Journal of Theoretical and Applied Information Technology, 100(21), 6610-6620.
Reynaldi, D., Negara, B. S., Sanjaya, S., & Satria, E. (2021, July). Covid-19 classification for chest x-ray images using deep learning and resnet-101. In 2021 International Congress of Advanced Technology and Engineering (ICOTEN) (pp. 1-4). IEEE.
Sarwinda, D., Paradisa, R. H., Bustamam, A., & Anggia, P. (2021). Deep learning in image classification using residual network (ResNet) variants for detection of colorectal cancer. Procedia Computer Science, 179, 423-431.
Lin, S. L. (2021). Application combining VMD and ResNet101 in intelligent diagnosis of motor faults. Sensors, 21(18), 6065.
Zhang, Q. (2022). A novel ResNet101 model based on dense dilated convolution for image classification. SN Applied Sciences, 4, 1-13.
Rathnayake, N., Rathnayake, U., Dang, T. L., & Hoshino, Y. (2022). An efficient automatic fruit-360 image identification and recognition using a novel modified cascaded-ANFIS algorithm. Sensors, 22(12), 4401.
Hasnain, M., Pasha, M. F., Ghani, I., Imran, M., Alzahrani, M. Y., & Budiarto, R. (2020). Evaluating trust prediction and confusion matrix measures for web services ranking. IEEE Access, 8, 90847-90861.
Heydarian, M., Doyle, T. E., & Samavi, R. (2022). MLCM: Multi-label confusion.
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.
