RESUMO
This paper explores a data augmentation approach for images of rigid bodies, particularly focusing on electrical equipment and analogous industrial objects. By leveraging manufacturer-provided datasheets containing precise equipment dimensions, we employed straightforward algorithms to generate synthetic images, permitting the expansion of the training dataset from a potentially unlimited viewpoint. In scenarios lacking genuine target images, we conducted a case study using two well-known detectors, representing two machine-learning paradigms: the Viola-Jones (VJ) and You Only Look Once (YOLO) detectors, trained exclusively on datasets featuring synthetic images as the positive examples of the target equipment, namely lightning rods and potential transformers. Performances of both detectors were assessed using real images in both visible and infrared spectra. YOLO consistently demonstrates F1 scores below 26% in both spectra, while VJ's scores lie in the interval from 38% to 61%. This performance discrepancy is discussed in view of paradigms' strengths and weaknesses, whereas the relatively high scores of at least one detector are taken as empirical evidence in favor of the proposed data augmentation approach.
RESUMO
Resumen La utilización de los colorantes en los procesos de identificación en microbiología se fundamenta en las propiedades fisicoquímicas de estas sustancias. En el campo de la física, la óptica explica cómo todos los objetos son observables dependiendo de las longitudes de onda que se absorben y se transmiten dentro del denominado "espectro visible". Dichas transiciones se deben, a su vez, a los compuestos químicos y a los movimientos electrónicos dentro de los átomos. Así mismo, cuando interacciona un colorante con una célula o un tejido, ocurren reacciones que dependen de grupos químicos funcionales denominados cromóforos y auxocromos. Dependiendo de los compuestos químicos que los constituyen, los colorantes pueden ser ácidos, básicos o neutros y esta connotación se debe a la parte activa del colorante y a la reacción que ocasiona sobre las células microbianas. De otra parte, las tinciones en microbiología pueden ser simples o diferenciales, dependiendo si toda la muestra se tiñe de uno o más colorantes. En el primer caso se encuentra el ejemplo de la coloración con azul de lactofenol y en el segundo, la coloración de Gram. En el presente artículo se reseñan las principales coloraciones utilizadas en microbiología y se explican los fundamentos físicos y químicos de dichos procesos.
Abstract The use of dyes in the identification processes in microbiology is based on the physicochemical properties of these substances. In the field of physics, optics explains how all objects are observable depending on the wavelengths that are absorbed and transmitted within the so-called "visible spectrum". These transitions are, in turn, due to chemical compounds and the electronic movements within atoms. Likewise, when a dye interacts with a cell or tissue, reactions occur that depend on functional chemical groups called chromophores and auxochromes. Depending on the chemical compounds that constitute them, the dyes can be acidic, basic or neutral and this connotation is due to the active part of the dye and the reaction it causes on the microbial cells. On the other hand, stains in microbiology can be simple or differential, depending on whether the entire sample is stained with one or more dyes. In the first case is the example of the lactophenol blue staining and in the second, the Gram staining. This article describes the main colorations used in microbiology and explains the physical and chemical foundations of these processes.