A Neural Network Architecture for Visual Selection

This paper describes a parallel neural net architecture for efficient and robust attentive visual selection in real generic gray level images. Objects are represented through flexible star type planar arrangements of binary local features, which are in turn star type planar arrangements of oriented edges. Candidate locations are detected over a range of scales and other deformations. The flexibility of the arrangements provides the required invariance. Training involves selecting a small number of stable local features, from a predefined pool, which are well localized on registered examples of the object. Training therefore requires only small data sets. No changes need to be made to the network for detecting new objects except for learning their representation in the memory module. Analogies between the different layers in the network and those in the visual system are discussed, furthermore we show how this model can be used to explain certain experiments on visual selection reported..