Recognition of isolated and simply connected hand-written numerals
Pattern Recognition
Optical character recognition by the method of moments
Computer Vision, Graphics, and Image Processing
Multiresolution elastic matching
Computer Vision, Graphics, and Image Processing
Computer graphics: principles and practice (2nd ed.)
Computer graphics: principles and practice (2nd ed.)
Hands: a pattern theoretic study of biological shapes
Hands: a pattern theoretic study of biological shapes
Reading cursive handwriting by alignment of letter prototypes
International Journal of Computer Vision
Elastic matching of multimodality medical images
CVGIP: Graphical Models and Image Processing
Handwritten digit recognition with a back-propagation network
Advances in neural information processing systems 2
Integrated segmentation and recognition of hand-printed numerals
NIPS-3 Proceedings of the 1990 conference on Advances in neural information processing systems 3
Handwritten numerical recognition based on multiple algorithms
Pattern Recognition
Neural Computation
Hand-printed digit recognition using deformable models
Proceedings of the 1991 York conference on Spacial vision in humans and robots
Neural Computation
Perceptual Organization and Visual Recognition
Perceptual Organization and Visual Recognition
A Database for Handwritten Text Recognition Research
IEEE Transactions on Pattern Analysis and Machine Intelligence
Efficient Pattern Recognition Using a New Transformation Distance
Advances in Neural Information Processing Systems 5, [NIPS Conference]
The acoustic-modeling problem in automatic speech recognition
The acoustic-modeling problem in automatic speech recognition
Combining deformable models and neural networks for handprinted digit recognition
Combining deformable models and neural networks for handprinted digit recognition
Representation and Recognition of Handwritten Digits Using Deformable Templates
IEEE Transactions on Pattern Analysis and Machine Intelligence
IEEE Transactions on Pattern Analysis and Machine Intelligence
Structure Extraction from Decorated Characters Using Multiscale Images
IEEE Transactions on Pattern Analysis and Machine Intelligence
IEEE Transactions on Pattern Analysis and Machine Intelligence
Bidirectional Deformable Matching with Application to Handwritten Character Extraction
IEEE Transactions on Pattern Analysis and Machine Intelligence
Training products of experts by minimizing contrastive divergence
Neural Computation
Deformable Template Matching within a Bayesian Framework for Hand-Written Graphic Symbol Recognition
GREC '99 Selected Papers from the Third International Workshop on Graphics Recognition, Recent Advances
ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 1
ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 1
A model for image generation and symbol recognition through the deformation of lineal shapes
Pattern Recognition Letters
Shape Understanding: Knowledge Generation and Learning
IEEE Transactions on Knowledge and Data Engineering
Development of a Structural Deformable Model for Handwriting Recognition
ICPR '98 Proceedings of the 14th International Conference on Pattern Recognition-Volume 2 - Volume 2
Data Driven Image Models through Continuous Joint Alignment
IEEE Transactions on Pattern Analysis and Machine Intelligence
Multi-template GAT Correlation for Character Recognition with a Limited Quantity of Data
ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition
Neural Computation
Images, Frames, and Connectionist Hierarchies
Neural Computation
Robust locally linear embedding
Pattern Recognition
Knowledge reuse in genetic programming applied to visual learning
Proceedings of the 9th annual conference on Genetic and evolutionary computation
Text search for medieval manuscript images
Pattern Recognition
Generative learning of visual concepts using multiobjective genetic programming
Pattern Recognition Letters
Multitask visual learning using genetic programming
Evolutionary Computation
Object localisation using the Generative Template of Features
Computer Vision and Image Understanding
Learning and Recognition of Hand-Drawn Shapes Using Generative Genetic Programming
Proceedings of the 2007 EvoWorkshops 2007 on EvoCoMnet, EvoFIN, EvoIASP,EvoINTERACTION, EvoMUSART, EvoSTOC and EvoTransLog: Applications of Evolutionary Computing
Detecting and reading text in natural scenes
CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
Registration of infra-red and visible-spectrum imagery for face recognition
FGR' 04 Proceedings of the Sixth IEEE international conference on Automatic face and gesture recognition
k-NN classification of handwritten characters via accelerated GAT correlation
Pattern Recognition
Hi-index | 0.14 |
We describe a method of recognizing handwritten digits by fitting generative models that are built from deformable B-splines with Gaussian "ink generators" spaced along the length of the spline. The splines are adjusted using a novel elastic matching procedure based on the Expectation Maximization (EM) algorithm that maximizes the likelihood of the model generating the data. This approach has many advantages. 1) After identifying the model most likely to have generated the data, the system not only produces a classification of the digit but also a rich description of the instantiation parameters which can yield information such as the writing style. 2) During the process of explaining the image, generative models can perform recognition driven segmentation. 3) The method involves a relatively small number of parameters and hence training is relatively easy and fast. 4) Unlike many other recognition schemes, it does not rely on some form of pre-normalization of input images, but can handle arbitrary scalings, translations and a limited degree of image rotation. We have demonstrated our method of fitting models to images does not get trapped in poor local minima. The main disadvantage of the method is it requires much more computation than more standard OCR techniques.