Deformation Models for Image Recognition
- 25 June 2007
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 29 (8) , 1422-1435
- https://doi.org/10.1109/tpami.2007.1153
Abstract
We present the application of different nonlinear image deformation models to the task of image recognition. The deformation models are especially suited for local changes as they often occur in the presence of image object variability. We show that, among the discussed models, there is one approach that combines simplicity of implementation, low-computational complexity, and highly competitive performance across various real-world image recognition tasks. We show experimentally that the model performs very well for four different handwritten digit recognition tasks and for the classification of medical images, thus showing high generalization capacity. In particular, an error rate of 0.54 percent on the MNIST benchmark is achieved, as well as the lowest reported error rate, specifically 12.6 percent, in the 2005 international ImageCLEF evaluation of medical image specifically categorization.Keywords
This publication has 42 references indexed in Scilit:
- A Survey of Elastic Matching Techniques for Handwritten Character RecognitionIEICE Transactions on Information and Systems, 2005
- Adaptation in statistical pattern recognition using tangent vectorsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- Handwritten digit recognition: benchmarking of state-of-the-art techniquesPattern Recognition, 2003
- Eigen-deformations for elastic matching based handwritten character recognitionPattern Recognition, 2003
- Robust vision-based features and classification schemes for off-line handwritten digit recognitionPattern Recognition, 2002
- Recognizing handwritten digits using hierarchical products of expertsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- A numeral character recognition using the PCA mixture modelPattern Recognition Letters, 2002
- Metrics and models for handwritten character recognitionStatistical Science, 1998
- Modeling the manifolds of images of handwritten digitsIEEE Transactions on Neural Networks, 1997
- Keyword spotting in poorly printed documents using pseudo 2-D hidden Markov modelsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1994