Selective Attention for Handwritten Digit Recognition
Ethem Alpaydın · 1995
Completely parallel object recognition is NP-complete. Achieving a recognizer with feasible complexity requires a compromise between parallel and sequential processing where a system selectively focuses on parts of a given image, one after another. Successive fixations are generated to sample the image and these samples are processed and abstracted to generate a temporal context in which results are integrated over time. A computational model based on a partially recurrent feedforward network is proposed and made credible by testing on the real-world problem of recognition of handwritten digits with encouraging results. 1 INTRODUCTION For all-parallel bottom-up recognition, allocating one separate unit for each possible feature combination, i.e., conjunctive encoding, implies combinatorial explosion. It has been shown that completely parallel, bottom-up visual object recognition is NP-complete (Tsotsos, 1990). By exchanging space with time, systems with much less complexity may be des...