Efficient Pattern Recognition Using a New Transformation Distance

Abstract

Memory-based classification algorithms such as radial basis functions or K-nearest neighbors typically rely on simple distances (Euclidean, dot product...), which are not particularly 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 Post Office and the NIST. Using invariances with respect to translation, rotation, scaling, shearing and line thickness, the method consistently outperformed all other systems tested on the same databases.

Keywords

Euclidean distanceNISTComputer sciencePattern recognition (psychology)Dot productScalingArtificial intelligenceInvariant (physics)k-nearest neighbors algorithmTranslation (biology)Transformation (genetics)AlgorithmMathematicsSpeech recognitionGeometry

Affiliated Institutions

Related Publications

Shape Classification Using the Inner-Distance

Haibin Ling , David W. Jacobs

Part structure and articulation are of fundamental importance in computer and human vision. We propose using the inner-distance to build shape descriptors that are robust to art...

2007 IEEE Transactions on Pattern Analysis... 1063 citations

Object recognition from local scale-invariant features

David Lowe

An object recognition system has been developed that uses a new class of local image features. The features are invariant to image scaling, translation, and rotation, and partia...

1999 15989 citations

Image Super-Resolution With Sparse Neighbor Embedding

Xinbo Gao , Kaibing Zhang , Dacheng Tao +1 more

Until now, neighbor-embedding-based (NE) algorithms for super-resolution (SR) have carried out two independent processes to synthesize high-resolution (HR) image patches. In the...

2012 IEEE Transactions on Image Processing 312 citations

Anchored Neighborhood Regression for Fast Example-Based Super-Resolution

Radu Timofte , Vincent De , Luc Van Gool

Recently there have been significant advances in image up scaling or image super-resolution based on a dictionary of low and high resolution exemplars. The running time of the m...

2013 1381 citations

Scale-invariant heat kernel signatures for non-rigid shape recognition

Michael M. Bronstein , Iasonas Kokkinos

One of the biggest challenges in non-rigid shape retrieval and comparison is the design of a shape descriptor that would maintain invariance under a wide class of transformation...

2010 690 citations

Publication Info

Year: 1992
Type: article
Volume: 5
Pages: 50-58
Citations: 464
Access: Closed

External Links

Citation Metrics

464

OpenAlex

Cite This

APA Style

                            
                                    Patrice Simard, 
                                
                                    Yann LeCun, 
                                
                                    John S. Denker
                                
                            (1992). 
                            Efficient Pattern Recognition Using a New Transformation Distance. 
                            Neural Information Processing Systems
                            , 5
                            
                            , 50-58.