We describe a method to compute the Euler number of a binary digital image based on a codification of contour pixels of the image's shapes. The overall procedure evolves from a set of lemmas and theorems, their demonstration and their numerical validation. The method is supported through an experimental set which analyzes some digital images and their outcome to demonstrate the applicability of the procedure. The paper also includes a discussion about present and futures steps on this research.
Neuromorphic computing is a recent class of brain-inspired high-performance computer platforms and algorithms involving biologically-inspired models adopting hardware implementation in integrated circuits. The neuromorphic computing applications have provoked the rise of highly connected neurons and synapses in analog circuit systems that can be used to solve today's challenging machine learning problems. In conjunction with biologically plausible learning rules, such as the Hebbian learning and memristive devices, biologically-inspired spiking neural networks are considered the next-generation neuromorphic hardware construction blocks that will enable the deployment of new analog in situ learning capable and energetic efficient brain-like devices. These features are envisioned for modern mobile robotic implementations, currently challenging to overcome the pervasive von Neumann computer architecture. This study proposes a new neural architecture using the spike-time-dependent plasticity learning method and step-forward encoding algorithm for a self tuning neural control of motion in a joint robotic arm subjected to dynamic modifications. Simulations were conducted to demonstrate the proposed neural architecture's feasibility as the network successfully compensates for changing dynamics at each simulation run.
A Kalman filter can be used to fill space–state reconstruction dynamics based on knowledge of a system and partial measurements. However, its performance relies on accurate modeling of the system dynamics and a proper characterization of the uncertainties, which can be hard to obtain in real-life scenarios. In this work, we explore how the values of a Kalman gain matrix can be estimated by using spiking neural networks through a combination of biologically plausible neuron models with spike-time-dependent plasticity learning algorithms. The performance of proposed neural architecture is verified with simulations of some representative nonlinear systems, which show promising results. This approach traces a path for its implementation in neuromorphic analog hardware that can learn and reconstruct partial and changing dynamics of a system without the massive power consumption that is typically needed in a Von Neumann-based computer architecture.
Resumen. El determinar el número de hoyos o de huecos de un objeto es de particular interés en aplicaciones diversas en el campo del análisis de imágenes, por ejemplo, en el control de calidad de piezas forjadas industrialmente. En la literatura aparecen reportados pocos métodos. La mayoría utiliza al menos cuatro o cinco operaciones aritméticas. En este artículo se presentan dos formulaciones para el cálculo exacto del número de hoyos de un objeto binario 2-D. La primera formulación es útil para el caso de objetos 4-conectados, la segunda puede ser utilizada en el caso de objetos con conectividad tipo 8. Ambas formulaciones emplean un número mínimo de comparaciones; son demostradas teóricamente y validadas numéricamente en su operación a través de con un conjunto de objetos o formas de diferente complejidad y cantidad de hoyos. Palabras clave: objeto conectado, forma conectada, Imagen binaria, bit-quad, número de hoyos. Formulations for the Efficient Computation of the Number of Holes of 2-D Binary Object Abstract. Determining the number of wholes of an object is of particular interest in several applications in the area of image analysis, for example, quality control of industrial machined parts. In literature we do not find too many methods. Most of them utilize at least four or five arithmetic operations. In this paper two formulations to compute the number of holes of a 2-D binary objet are provided. The first formulation is valid for the case of 4-connected objects, the second one can be used in the case of 8-connected shapes. Both formulations employ a reduced number of comparisons, and are theoretically demonstrated and numerically validated by using a set of objects of different complexity and number of holes.
Resumen. En este artículo se presenta un sistema de control supervisado que planea los movimientos de un robot humanoide. El sistema propuesto es una estructura de supervisión formada por dos niveles jerárquicos de un sistema a eventos discretos. La parte superior está representada por una red de Petri que se comporta como un supervisor que indica la secuencia de movimientos que el robot debe realizar. Por otro lado, el nivel inferior está representado por un robot humanoide en un ambiente controlado. Las decisiones del robot durante la fase de exploración es modelada mediante una configuración de lógica difusa que utiliza un Sistema Difuso de Inferencia (SDI).
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.