Object segmentation using an array of interconnected neural networks with local receptive fields

We introduce an architecture for object segmentation/recognition that overcomes some limitations of classical neural networks by utilizing contextual information. An important characteristic of our model is that recognition is treated as a process of discovering a pattern rather than a one-time comparison between a pattern and a stored template. Our network implements some properties of human perception and during the recognition emulates the process of saccadic eye movements. We contrast our model to hidden Markov models in application to segmentation/recognition of handwriting and demonstrate a number of advantages.