Abstract

The automation of fruit detection and classification has become a vital component of modern precision agriculture. Real-time video processing enables dynamic and continuous fruit identification, offering significant potential for sorting, grading, and quality assessment applications. This paper presents an efficient feature extraction approach for real-time pomegranate identification using first and second-order statistical measures. The statistical features mean, standard deviation, skewness, energy, entropy, contrast, homogeneity and correlation are derived from image frames captured in real-time video sequences using the Python OpenCV library. These features are then used to train and evaluate multiple machine learning classifiers, including Logistic Regression (LR), Linear Discriminant Analysis (LDA), Support Vector Machine (SVM), Decision Tree (DT) and k-Nearest Neighbors (k-NN). These classifiers are evaluated using confusion matrix, accuracy, precision, recall, and F1-score metrics. The experimental results show that first and second-order statistical features provide a computationally efficient and reliable representation for real-time fruit classification. Among the evaluated models, Logistic Regression achieved the highest classification accuracy of 76.19%. The findings demonstrate that statistical feature based techniques can be lightweight alternatives to deep learning approaches for resource constrained agricultural automation systems.

References

• Gonzalez, R. C., and Woods, R. E. 2018. Digital Image Processing, 4th ed., Pearson.
• Ren, A., Zahid, A., Zoha, A., Shah, S. A., Imran, M. A., Alomainy, A., and Abbasi, A. 2020. Machine learning driven approach towards the quality assessment of fresh fruits using non-invasive sensing. IEEE Sensors Journal, 20(4), 2075–2083. 3] Jia, W., Xu, Y., Lu, Y., Yin, X., Pan, N., Jiang, R., and Ge, X. 2023. An accurate green fruits detection method based on optimized YOLOX-m. Frontiers in Plant Science, 14, 1187734.
• Chen, M. C., Cheng, Y. T., and Liu, C. Y. 2022. Implementation of a fruit quality classification application using an artificial intelligence algorithm. Sensors and Materials, 34(1).
• Ghazal, S., Qureshi, W. S., Khan, U. S., Iqbal, J., Rashid, N., and Tiwana, M. I. 2021. Analysis of visual features and classifiers for fruit classification problem. Computers and Electronics in Agriculture, 187.
• Yoshida, T., Kawahara, T., and Fukao, T. 2022. Fruit recognition method for a harvesting robot with RGB-D cameras. ROBOMECH Journal.
• Kondo, N. 2010. Automation on fruit and vegetable grading system and food traceability. Trends in Food Science & Technology, 21, 145–152.
• Gill, H. S., Murugesan, G., Mehbodniya, A., and Sajja, G. S. 2023. Fruit type classification using deep learning and feature fusion. Computers and Electronics in Agriculture, 211.
• Yuan, Y., and Chen, X. 2024. Vegetable and fruit freshness detection based on deep features and principal component analysis. Current Research in Food Science, 8.
• Raut, S. D., and Mashalkar, J. V. 2024. ICAMIDA 2022. ACSR, 105, 943–952.