Félix Ramos's Lab
About the lab
Featured projects (1)
Featured research (2)
The visual system provides with relevant information to create an internal representation of the environment and with this information to make decisions. Visual information is primarily processed in the visual cortex, where neurons react to certain visual features. In computational neuroscience and artificial vision, the study and modeling of vision processes is a topic of great interest since the human visual system can process a great diversity of stimuli in a wide variety of conditions. In this work, we propose a computational framework inspired by the human visual system, that integrates models obtained from neuroscience to describe aspects of vision such as color processing and shape processing and thus contribute to formulating a general vision system and incorporating it into artificial entities in order to approximate human behavior. This system covers the early stages of visual sensory processing, in addition to intermediate processing stages, and considers connections with other cognitive functions within a cognitive architecture. In this proposal, the model is formally described, and the results obtained are analyzed qualitatively to later weigh the considerations for the expansion of this framework.
Human beings can effortlessly perceive stimuli through their sensory systems to learn, understand, recognize and act on our environment or context. Over the years, efforts have been made to enable cybernetic entities to be close to performing human perception tasks; and in general, to bring artificial intelligence closer to human intelligence. Neuroscience and other cognitive sciences provide evidence and explanations of the functioning of certain aspects of visual perception in the human brain. Visual perception is a complex process, and its has been divided into several parts. Object classification is one of those parts; it is necessary for carrying out the declarative interpretation of the environment. This article deals with the object classification problem. In this article, we propose a computational model of visual classification of objects based on neuroscience, it consists of two modular systems: a visual processing system, in charge of the extraction of characteristics; and a perception sub-system, which performs the classification of objects based on the features extracted by the visual processing system. With the results obtained, a set of aspects are analyzed using similarity and dissimilarity matrices. Also based on the neuroscientific evidence and the results obtained from this research, some aspects are suggested for consideration to improve the work in the future and bring us closer to performing the task of visual classification as humans do.