CCMT: Dataset for crop pest and disease detection.

Artificial Intelligence (AI) has been evident in the agricultural sector recently. The objective of AI in agriculture is to control crop pests/diseases, reduce cost, and improve crop yield. In developing countries, the agriculture sector faces numerous challenges in the form of knowledge gap between farmers and technology, disease and pest infestation, lack of storage facilities, among others. In order to resolve some of these challenges, this paper presents crop pests/disease datasets sourced from local farms in Ghana. The dataset is presented in two folds; the raw images which consists of 24,881 images (6,549-Cashew, 7,508-Cassava, 5,389-Maize, and 5,435-Tomato) and augmented images which is further split into train and test sets. The latter consists of 102,976 images (25,811-Cashew, 26,330-Cassava, 23,657-Maize, and 27,178-Tomato), categorized into 22 classes. All images are de-identified, validated by expert plant virologists, and freely available for use by the research community.

Uncertainty Estimation Using Variational Mixture of Gaussians Capsule Network for Health Image Classification.

Capsule Networks have shown great promise in image recognition due to their ability to recognize the pose, texture, and deformation of objects and object parts. However, the majority of the existing capsule networks are deterministic with limited ability to express uncertainty. Many of them tend to be overconfident on out-of-distribution data, making them less trustworthy and hence reducing their suitability for practical adoption in safety-critical areas such as health and self-driving cars. In this work, we propose a capsule network based on a variational mixture of Gaussians to train distributions of network weights as opposed to a single set of weights and enable the model to express its predictive uncertainty on out-of-distribution data. Training distributions of weights have the added advantage of avoiding overfitting on smaller datasets which are common in health and other fields. Although Bayesian neural networks are known to exhibit slow training and convergence, experimental results show that the proposed model can retrieve only relevant features, converge faster, is less computationally complex, can effectively express its predictive uncertainties, and achieve performance values that are comparable to the state-of-the-art models. This is an indication that CapsNets can exhibit the transparency, credibility, reliability, and interpretability required for practical adoption.

GC3558: An open-source annotated dataset of Ghana currency images for classification modeling.

The field of deep learning has led to remarkable advancements in many areas, including banking. Identifying currency denomination type and model is challenging due to intraclass variation and different illumination conditions. Although, in this domain, many datasets regarding currency denomination type and model, e.g., Indian Currency, Thai Currency, Chinese Currency, U.K. currency, etc., have already been experimented with by different researchers. More datasets are needed from a variety of currencies, especially Ghana currency (cedi). This article presents the Ghana Currency image dataset (GC3558) of 3558 color images in 13 classes created from a high-resolution camera. The dataset is comprised of only genuine currency. The class consists of coin and paper notes: 10 pesewas coin, 20 pesewas coin, 50 pesewas coin, 1 cedi coin, 2 cedis coin, 1 cedi note, 2 cedis note, 5 cedis note, 10 cedis note, 20 cedis note, 50 cedis note, 100 cedis note and 200 cedis note. All images are de-identified, validated, and freely available for download to A.I. researchers. The dataset will help researchers evaluate their machine learning models on real-world data.