A novel plant disease diagnosis framework by integrating semi-supervised and ensemble learning

Plant disease diagnosis is one of the latest critical research areas of sustainable agriculture. The evolution of computer vision-based systems in order to identify, classify and localize diseases has automated the process of plant disease identification. CNNs are the pre-eminent deep learning-based algorithms used to automate plant disease recognition that has proven decisive on various benchmarks. However, a substantial part of the research lacks adequate attention to specific issues like the unavailability of datasets, high annotation costs and non-conformity of the models. Therefore, there is a pressing need to exploit the latest trends and technologies in this area to solve the above-mentioned problems. As a step ahead in this direction, a new framework has been proposed using semi-supervised & ensemble learning. The proposed framework is validated through a series of experiments on benchmark datasets. The results reported a significant performance improvement in classifying plant diseases, outperforming existing works with an improvement of 18.03% and 15% regarding the accuracy and F1 score, respectively. The mean average precision for detection is improved by 13.35%. Findings from this research will be beneficial for farmers, plant pathologists and researchers, which in turn will strengthen the sustainable facet of agriculture.