We propose a new distance measure which: 1) can be made locally invariant to any set of transformations of the input; and 2) can be computed efficiently. We ...

Dive into the research topics of 'Memory-based character recognition using a transformation invariant metric'. Together they form a unique fingerprint. Data ...

We propose a new distance measure which: 1) can be made locally invariant to any set of transformations of the input; and 2) can be computed efficiently. We ...

We propose a new distance measure which: 1) can be made locally invariant to any set of transformations of the input; and 2) can be computed efficiently. We ...

Dive into the research topics of 'Memory-based character recognition using a transformation invariant metric'. Together they form a unique fingerprint. Sort by ...

Inproceedings,. Memory-based character recognition using a transformation invariant metric. P. Simard, Y. LeCun, and ...

In optical character recognition (OCR), for in- stance, we know that the classification should be invariant under a set of transformations like rotation or ...

Memory Based Character Recog itio Usi g a Tra sformatio I varia t Metric. Patrice B. SimarI. Bann Le Cun. John S. Denker. ATZT Bell Laboratories. HolmIel, NJ ...

A novel invariant pattern recognition approach is proposed based on a special gradient-type recurrent analog associative memory. The system exhibits stable ...

We propose a new modular classification system based on several autoassociative multilayer perceptrons which allows the efficient incorporation of such ...