Model-based recognition in robot vision
ACM Computing Surveys (CSUR)
Generating and generalizing models of visual objects
Artificial Intelligence
Feature identification for hybrid structural/statistical
Computer Vision, Graphics, and Image Processing
Algebraic Description of Curve Structure
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Mechanism of Automatic 3D Object Modeling
IEEE Transactions on Pattern Analysis and Machine Intelligence
Model-Based Shape Matching with Structural Feature Grouping
IEEE Transactions on Pattern Analysis and Machine Intelligence
Organizing Large Structural Modelbases
IEEE Transactions on Pattern Analysis and Machine Intelligence
Structural feature extraction using multiple bases
Computer Vision and Image Understanding
Building three-dimensional object models from image sequences
Computer Vision and Image Understanding
An approach to integration of off-line and on-line recognition of handwriting
Pattern Recognition Letters
A structural model of curve deformation by discontinuous transformations
Graphical Models and Image Processing
Shape recognition by integrating structural descriptions and geometrical/statistical transforms
Computer Vision and Image Understanding
Learning and reasoning by analogy
Communications of the ACM
Learning Visual Models from Shape Contours Using Multiscale Convex/Concave Structure Matching
IEEE Transactions on Pattern Analysis and Machine Intelligence
The Automatic Construction of a View-Independent Relational Model for 3-D Object Recognition
IEEE Transactions on Pattern Analysis and Machine Intelligence
An Algebraic Approach to Automatic Construction of Structural Models
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Shape Analysis Model with Applications to a Character Recognition System
IEEE Transactions on Pattern Analysis and Machine Intelligence
On-Line Cursive Kanji Character Recognition Using Stroke-Based Affine Transformation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Structure Extraction from Decorated Characters Using Multiscale Images
IEEE Transactions on Pattern Analysis and Machine Intelligence
ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 1
| Hi-index | 0.15 |
We present an approach to automatic construction of structural models incorporating discontinuous transformations, with emphasis on application to unconstrained handwritten character recognition. We consider this problem as constructing inductively, from the data set, some shape descriptions that tolerate certain types of shape transformations. The approach is based on the exploration of complete, systematic, high-level models on the effects of the transformations, and the generalization process is controlled and supported by the high-level transformation models. An analysis of the a priori effects of commonly occurring discontinuous transformations is carried out completely and systematically, leading to a small, tractable number of distinct cases. Based on this analysis, an algorithm for the inference of super-classes under these transformations is designed. Furthermore, through examples and experiments, we show that the proposed algorithm can generalize unconstrained handwritten characters into a small number of classes, and that one class can represent various deformed patterns.