Este artículo presenta el análisis y la metodología de implementación de la técnica de localización de raíces de sistemas dinámicos para la planeación de rutas libres de obstáculos para robots móviles. En primera instancia, se realiza un análisis e identificación del comportamiento morfológico de las trayectorias en dependencia de la ubicación de las raíces en el plano complejo, identificándose el tipo de trayectorias curvas y la característica de atracción y repulsión de estas en presencia de otras raíces, de forma similar al obtenido con la técnica de cargas de potencial artificial. Se plantea una metodología para implementación de esta técnica para la planeación de rutas de robots móviles, partiendo de tres métodos diferentes de ubicación de las raíces para los obstáculos presentes en el escenario. Dichas técnicas varían dependiendo de los puntos clave del obstáculo que son seleccionados para las raíces, tales como los bordes, los cruces con las trayectoria original, el centro y los vértices. Finalmente, se realiza un análisis de funcionamiento de la técnica en general y de la efectividad cada uno de los métodos evaluados, bajo 20 pruebas para cada uno, obteniendo un valor del 65% para el método seleccionado. También se proponen modificaciones o posibles mejoras a la metodología propuesta.
The recognition systems of patterns in images are mechanisms that filter the information that provides an image to highlight the area of interest for the user. Usually, these mechanisms are based on mathematical transformations that allow the processor to perform interpretations based on the geometry or shape of the image. However, the strategies that implement mathematical transformations are limited, since the effectiveness of these techniques is reduced by changing the morphology or resolution of the image. This paper presents a partial solution to this limitation with a digital image processing technique based on a deep learning neural network (DNN). This technique incorporates a mechanism that allows the DNN to determine the facial expression of a person, based on the segmented information of the image of their face. By segmenting the image and processing its characteristics in parallel, the proposed technique increases the effectiveness of recognizing facial gestures in different images even when modifying their characteristics.
The constant change and transformation in organizations have made markets increasingly innovative and competitive, creating in this way the need to incorporate advanced technology to capture, process and analyze information from the current environment through the use of tools and / or instruments that facilitate decision making in an accurate way and even anticipate in their markets, making this a strategic increase for the organization. The objective of this paper is to carry out an analysis and contextualization in relation to Technological Surveillance Systems, with the purpose of exposing the characteristics and elements of management in the framework of technological surveillance. On the other hand, it will be introduced to the phases that make up a Technological Surveillance process, emphasizing the methodology for the selection of ICT / software tools. Finally, some of the existing tools in the market that allow successfully carry out each of the phases of this process are described.
This document shows the design of a software for the detection of very pronounced edges, fissures and fractures of bone structures in radiological images, using image processing techniques as an enhancement method. A graphic interface was used for the user to select the bone to inspect, by means of an object labeling algorithm, the coordinates of said bone, "region of interest" ROI are identified, after which the thresholding of the image will be performed, then a series of morphological operations will be applied and in this way the detection of the lesion, which is highlighted by the change of color for the visualization in the output image, making an overlap of the fissures and / or fractures in the original image.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.