RESUMO
Cassava is a most important carbohydrate human food consumed in many African and Asian countries. Cassava leaf disease is the major issue which affects production. Automatic early cassava leaf disease detection through deep learning models and transfer learning models were used for multiclass classification with different approaches. Existing approaches deal with imbalanced dataset for predicting the classes. This research work develops an approach based on hybrid Ensemble - deep transfer model approach for early leaf disease detection. Data augmentation was applied to the raw data for balancing the dataset. Three distinct new hybrid models namely Ensemble(InceptionV3+DenseNet-BC-121-32 + Xception), Ensemble(ResNet50V2+DenseNet-BC-121-32), Ensemble(ResNet50V2+ResNet50) were developed. The proposed model shows high performance results. A broad comparison of the proposed model was performed with custom based Convolutional Neural Network and pre-trained models. Highest accuracy of 88.83% and 97.89% was obtained in ensemble based approach that combined InceptionV3, Xception, DenseNet-BC-121-32 for five class and two class classification respectively.
RESUMO
Okra, renowned for its abundance of essential nutrients, emerges as a promising solution in addressing malnutrition, advocating for sustainable agriculture, and showcasing versatile untapped potentials. Our objective is to enhance the quality, market attractiveness, and culinary adaptability of okra harvests by classifying them into over-matured and adequately matured groups through a non-invasive approach. This dataset is centered on thermal images capturing different maturity levels of okra, categorized into two distinct groups. The thermal imaging device is employed for image capture, and the okra samples are sourced from diverse vegetable vendors and farms. This dataset proves to be a valuable asset for the non-invasive examination and categorization of okras based on their maturity levels.