Memory-based character recognition using a transformation invariant metric

Patrice Y. Simard, Yann Le Cun, John S. Denker

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Memory-based classification algorithms such as Radial Basis Functions or K-nearest neighbors often rely on simple distances (Euclidean distance, Hamming distance, etc.), which are rarely meaningful on pattern vectors. More complex, better suited distance measures are often expensive and rather ad-hoc (elastic matching, deformable templates). We propose a new distance measure which (a) can be made locally invariant to any set of transformations of the input and (b) can be computed efficiently. We tested the method on large handwritten character databases provided by the U.S. Post Office and NIST. Using invariances with respect to translation, rotation, scaling, skewing and line thickness, the method outperformed all other systems on a small (less than 10,000 patterns) database and was competitive on our largest (60,000 patterns) database.

Original languageEnglish (US)
Title of host publicationProceedings of the 12th IAPR International Conference on Pattern Recognition - Conference B
Subtitle of host publicationPattern Recognition and Neural Networks, ICPR 1994
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages262-267
Number of pages6
ISBN (Electronic)0818662700
StatePublished - 1994
Event12th IAPR International Conference on Pattern Recognition - Conference B: Pattern Recognition and Neural Networks, ICPR 1994 - Jerusalem, Israel
Duration: Oct 9 1994Oct 13 1994

Publication series

NameProceedings - International Conference on Pattern Recognition
Volume2
ISSN (Print)1051-4651

Conference

Conference12th IAPR International Conference on Pattern Recognition - Conference B: Pattern Recognition and Neural Networks, ICPR 1994
Country/TerritoryIsrael
CityJerusalem
Period10/9/9410/13/94

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Fingerprint

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

Cite this