Classifying cocoa beans, considering some specific standards, is required and regulated around the world, if commercialization is intended, or it can be very useful, in order to select the best ones for a given proposal. This article presents an image dataset of cut test classified cocoa beans, provided by experts following the Brazilian regulative norm for that process. Fourteen classes, with 100 images for each, were registered in a device designed with standard constant artificial lighting and capturing settings and will be present in this paper. Images are hosted in the Núcleo de Biologia Computacional from Universidade Estadual de Santa Cruz, under the "tedais" name.
There are some classification methods that generate nuances in the final accuracy caused by objects positioning, framing and damage. These occurrences may result in a drop of accuracy in computer vision systems that were trained with structured static datasets and are intended to be used in day-to-day applications in which the images are not always as organized as the trained dataset, like some biometric classification systems such as iris and fingerprint. In this regard, this paper presents six image datasets processed with different methods to help researchers analyze the impact of object positioning, framing and damage in their taxonomies.
Nowadays, using neural networks for image processing and tracking of individuals/objects is a highly popular subject that can be applied to various real-world issues. However, for such cases, the image often needs to possess good quality and exhibit distinct features to aid in object detection, posing challenges in environments with low or no illumination. In our work, we present a comparative study on the performance of leading convolutional neural networks for the detection and tracking of individuals through depth color images generated by infrared sensors. Additionally, we aim to demonstrate the usability of the YOLO (You Only Look Once) architecture as an alternative for identifying objects in images generated by sensors that do not rely on illumination. Experimental results showcase that the approach using YOLO Tiny improves accuracy by approximately 9% and processes around 8 times more frames per second (FPS).
Neurodegenerative diseases are a group of largely incurable disorders characterised by the progressive loss of neurons and for which often the molecular mechanisms are poorly understood. To bridge this gap, researchers employ a range of techniques. A very prominent and useful technique adopted across many different fields is imaging and the analysis of histopathological and fluorescent label tissue samples. Although image acquisition has been efficiently automated recently, automated analysis still presents a bottleneck. Although various methods have been developed to automate this task, they tend to make use of single-purpose machine learning models that require extensive training, imposing a significant workload on the experts and introducing variability in the analysis. Moreover, these methods are impractical to audit and adapt, as their internal parameters are difficult to interpret and change. Here, we present a novel unsupervised automated schema for object segmentation of images, exemplified on a dataset of tissue images. Our schema does not require training data, can be fully audited and is based on a series of understandable biological decisions. In order to evaluate and validate our schema, we compared it with a state-of-the-art automated segmentation method for post-mortem tissues of ALS patients.