Fruit Quality Detection Using Deep Learning Techniques

This article presented fruit quality detection using deep learning techniques. The work addresses the limitations of manual inspection and conventional image processing by proposing a hybrid CNN-SPP and SSDAE-SVM framework. The system processes fruit images, enhances them through preprocessing, extracts deep visual features, preserves spatial information using SPP, optimizes features using SSDAE, and classifies quality using SVM. The thesis results demonstrate that the proposed hybrid model achieves 97.25% accuracy, 98.10% precision, 98.98% recall, 98.81% F1-score, and 95.62% specificity. These values show that the model is effective for distinguishing fresh and rotten fruits. The hybrid approach is suitable projects because it includes image processing, deep learning, feature optimization, machine learning classification, performance evaluation, and practical system design. The proposed system has strong potential for agricultural automation, postharvest quality control, retail inspection, and smart supply chain applications. With larger datasets, real-time deployment, and multi-class grading support, the system can be developed into a more complete fruit quality assessment platform.

[1] A. Ren, A. Zahid, A. Zoha, S. A. Shah, M. A. Imran, A. Alomainy, and Q. H. Abbasi, "Machine learning-driven approach towards the quality assessment of fresh fruits using non-invasive sensing," IEEE Sensors Journal, vol. 20, no. 4, pp. 2075-2083, Feb. 2020. [2] E. Bellocchio, T. A. Ciafuglia, G. Costante, and P. Valigi, "Weakly supervised fruit counting for yield estimation using spatial consistency," IEEE Robotics and Automation Letters, vol. 4, no. 3, pp. 2348-2355, 2019. [3] G. Ciocca, G. Micali, and P. Napoletano, "State recognition of food images using deep features," IEEE Access, vol. 8, pp. 32003-32017, Feb. 2020. [4] G. Xuan, C. Gao, Y. Shao, M. Zhang, Y. Wang, J. Zhong, and Q. Li, "Apple detection in natural environment using deep learning algorithms," IEEE Access, vol. 8, pp. 216772-216780, 2020. [5] G. Zeng, "Fruit and vegetables classification system using image saliency and convolutional neural network," in Proc. IEEE 3rd Information Technology and Mechatronics Engineering Conf., 2017. [6] M. Muladi, D. Lestari, and D. T. Prasetyo, "Classification of eligibility consumption of Manalagi apple fruit varieties using backpropagation," in Proc. Int. Conf. Advanced Mechatronics, Intelligent Manufacture and Industrial Automation, 2019. [7] S. Luo, K. Sarabandi, L. Tong, and L. Pierce, "A SAR image classification algorithm based on multi-feature polarimetric parameters using FOA and LS-SVM," IEEE Access, vol. 7, pp. 175259-175276, Dec. 2019. [8] W. Castro, J. Oblitas, M. De-La Torre, C. Cotrina, K. Bazan, and H. A. George, "Classification of cape gooseberry fruit according to its level of ripeness using machine learning techniques," IEEE Latin America Transactions, 2019. [9] Y. Peng, M. Liao, Y. Song, Z. Liu, H. He, H. Deng, and Y. Wang, "FB-CNN: Feature fusion-based bilinear CNN for classification of fruit fly image," IEEE Access, vol. 8, pp. 2169-2180, 2020. [10] Y.-P. Huang, T.-H. Wang, and H. Basanta, "Using fuzzy Mask R-CNN model to automatically identify tomato ripeness," IEEE Access, vol. 8, pp. 207672-207682, Nov. 2020.