Object recognition by indexing using neural networks

Abstract

In this paper a new Distributed Neural Network Architecture (DNNA) for object recognition is presented. The proposed architecture is tested in two scenarios: occluded planar object recognition and face recognition. The DNNA is composed by several classifiers, each one with a standard ART2 Neural Network (ART2-NN) connected to a Memory Map (MM), a set of logical AND gates, an evidence register, and a set of comparators. In a first step, objects are described by a set of sub-feature vectors (SFV), during the training stage, each SFV is then fed to an ARR-NN to train it and to build its corresponding Memory Map (MM). During a second phase of indexing a new image possibly containing the object is used to retrieve fiom the previously constructed MM the list of candidate objects that are in the image. A selection threshold is finally used to select from this list the objects that most resemble the objects on the image.

Modelado de un sistema de supervisión de la calidad del aire usando técnicas de fusión de sensores y redes neuronales

“…Las redes neuronales han revolucionado el reconocimiento de patrones aplicado a diversas áreas. Algunos ejemplos incluyen: detección y reconocimiento facial [150,151], diagnósticos médicos [152], clasificación de imágenes satelitales [153], análisis y reconocimiento de textos [154], reconocimiento de objetos [155], reconocimiento de escritura a mano [156],…”