Simplifying surfaces using neural networks

• Grant number: 06/01016-4
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: September 01, 2006
• End date: August 31, 2007
• Field of knowledge: Engineering - Mechanical Engineering
• Principal Investigator: Glauco Augusto de Paula Caurin
• Grantee: Christoffer Tenório Emídio de Souza
• Host Institution: Escola de Engenharia de São Carlos (EESC). Universidade de São Paulo (USP). São Carlos , SP, Brazil

Abstract

This project aims at to simplify a surface that represents a solid object. The surface will be simplified using Neural Nets, in way that the result is the sufficient to inform the format of the object to be fixed by the artificial hand. This simplification will be used as daily pay-processing of intelligent systems with intention to reduce the number of points of definition of the object, diminishing and liberating the processing. The result will be used in BRAHMA (Brazilian Anthropomorphic Hand), artificial hand that is in development in the Laboratory of Mecatrônica of the School of Engineering of São Carlos (Eesc-usp); moreover, the system will have to be flexible to be applied in any area of vision, and for in such a way, an application study will be made to compare with other existing results. (AU)