.
| ESP Journal of Engineering & Technology Advancements |
| © 2026 by ESP JETA |
| Volume 6 Issue 4 |
| Year of Publication : 2026 |
| Author : Rahamath Mohamed Razikh Ulla |
10.56472/25832646/JETA-V6I4P106 |
Rahamath Mohamed Razikh Ulla, 2026. Convolutional Neural Networks for Real-World Classification: Lessons from Applied Image Recognition, Volume 6 Issue 4: 57-67.
Image classification using convolutional neural networks (CNNs) has revolutionized the manner in which images are recognized because the manually constructed descriptors have been substituted by the hierarchical learning of features which have been directly applied to the image pixel data. This family of architectures has enabled high performance in medical diagnostics, agriculture, remote sensing, manufacturing, food inspection and waste sorting but much of that performance has been demonstrated so far in conditions that are not as representative of the environment of operational practice as actual deployment environments. This survey explains the development of CNNs since the initial document-recognition systems to domain-specific applications in the real world, based on what can be learnt about implementation, and not on architecture novelty. Themes such as transfer learning, dataset curation, class imbalance, domain shift, compression-aware deployment, lightweight inference, interpretability, and performance reporting by operation constraints are some of the important ones. The literature examined suggests that the gains in accuracy can be substantial, but the issue of reliability in the area is a question of the quality of the information, the conditions under which it was obtained, the validity of the labelling, and the infrastructure of usage just as much as the issue of the complexity of the model underlying it. Restrictive variables such as the poor extrapolation of external variables, benchmark inflation using controlled imaging, insufficient analysis of calibration, and failure mode and fairness treatment are common. The sphere itself is highly important as the mediation of visual classification of the screening, monitoring, industrial inspection and management of the environment becomes more and more quick. Complex research agenda, therefore, requires higher-levels of assessment protocols, broader implementation using multimodal and more resource sensitive methods, and more integration of consistency between laboratory and actual operational judgment.
[1] LeCun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11), 2278–2324.
[2] Rawat, W., & Wang, Z. (2017). Deep convolutional neural networks for image classification: A comprehensive review. Neural Computation, 29(9), 2352–2449.
[3] Guo, Y., Liu, Y., Oerlemans, A., Lao, S., Wu, S., & Lew, M. S. (2016). Deep learning for visual understanding: A review. Neurocomputing, 187, 27–48.
[4] Esteva, A., Kuprel, B., Novoa, R. A., Ko, J., Swetter, S. M., Blau, H. M., & Thrun, S. (2017). Dermatologist-level classification of skin cancer with deep neural networks. Nature, 542(7639), 115–118.
[5] Litjens, G., Kooi, T., Bejnordi, B. E., Setio, A. A. A., Ciompi, F., Ghafoorian, M., van der Laak, J. A. W. M., van Ginneken, B., & Sánchez, C. I. (2017). A survey on deep learning in medical image analysis. Medical Image Analysis, 42, 60–88.
[6] Gulshan, V., Peng, L., Coram, M., Stumpe, M. C., Wu, D., Narayanaswamy, A., Venugopalan, S., Widner, K., Madams, T., Cuadros, J., Kim, R., Raman, R., Nelson, P. C., Mega, J. L., & Webster, D. R. (2016). Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA, 316(22), 2402–2410.
[7] Rajpurkar, P., Irvin, J., Ball, R. L., Zhu, K., Yang, B., Mehta, H., Duan, T., Ding, D., Bagul, A., Langlotz, C., Shpanskaya, K., Lungren, M. P., & Ng, A. Y. (2018). Deep learning for chest radiograph diagnosis: A retrospective comparison of the CheXNeXt algorithm to practicing radiologists. PLOS Medicine, 15(11), e1002686.
[8] Mohanty, S. P., Hughes, D. P., & Salathé, M. (2016). Using deep learning for image-based plant disease detection. Frontiers in Plant Science, 7, 1419.
[9] Ferentinos, K. P. (2018). Deep learning models for plant disease detection and diagnosis. Computers and Electronics in Agriculture, 145, 311–318.
[10] Ramcharan, A., Baranowski, K., McCloskey, P., Ahmed, B., Legg, J., & Hughes, D. P. (2017). Deep learning for image-based cassava disease detection. Frontiers in Plant Science, 8, 1852.
[11] Pires de Lima, R., & Marfurt, K. (2020). Convolutional neural network for remote-sensing scene classification: Transfer learning analysis. Remote Sensing, 12(1), 86.
[12] Yu, X., Liu, X., Zhou, X., & Huang, C. (2017). Deep learning in remote sensing scene classification: A data augmentation enhanced convolutional neural network framework. Geo-spatial Information Science, 20(2), 142–149.
[13] Ahn, J., Park, J., Park, D., Paek, J., & Ko, J. (2018). Convolutional neural network-based classification system design with compressed wireless sensor network images. PLOS ONE, 13(5), e0196251.
[14] Xing, J., Ng, T.-T., Chen, Y., Wang, H., Xie, M., & Yang, X. (2021). A convolutional neural network-based method for workpiece surface defect detection. Measurement, 176, 109022.
[15] Zheng, H., Li, X., Li, Y., Kim, M., & Kim, J. (2021). A deep convolutional neural network-based multi-class image classification for automatic wafer map failure recognition in semiconductor manufacturing. Applied Sciences, 11(20), 9769.
[16] Wang, Y., Chen, J., & Wang, J. (2021). Food image recognition and food safety detection method based on neural network. Computational Intelligence and Neuroscience, 2021, 5562784.
[17] Malik, M., Sharma, S., Uddin, M., Chen, C.-L., Wu, C.-M., Soni, P., & Chaudhary, S. (2022). Waste classification for sustainable development using image recognition with deep learning neural network models. Sustainability, 14(12), 7222.
[18] Laksono, P. W., Anisa, A., & Priyandari, Y. (2024). Deep learning implementation using convolutional neural network in inorganic packaging waste sorting. Franklin Open, 8, 100146.
[19] Yu, J., Schumann, A. W., Cao, Z., Sharpe, S. M., & Boyd, N. S. (2019). Weed detection in perennial ryegrass with deep learning convolutional neural network. Frontiers in Plant Science, 10, 1422.
[20] Khan, A. T., Jensen, S. M., Khan, A. R., & Li, S. (2023). Plant disease detection model for edge computing devices. Frontiers in Plant Science, 14, 1308528.
[21] Shin, E., & Yoo, C. D. (2023). Efficient convolutional neural networks for semiconductor wafer bin map classification. Sensors, 23(4), 1926.
Agricultural Image Analysis, Convolutional Neural Networks, Image Classification, Medical Imaging, Real-World Deployment, Transfer Learning