Reading cursive handwriting by alignment of letter prototypes
International Journal of Computer Vision
The Relative Neighborhood Graph, with an Application to Minimum Spanning Trees
Journal of the ACM (JACM)
Perceptual Organization and Visual Recognition
Perceptual Organization and Visual Recognition
A Shape Analysis Model with Applications to a Character Recognition System
IEEE Transactions on Pattern Analysis and Machine Intelligence
Selective Feature-to-Feature Adhesion for Recognition of Cursive Handprinted Characters
IEEE Transactions on Pattern Analysis and Machine Intelligence
Twenty Years of Document Image Analysis in PAMI
IEEE Transactions on Pattern Analysis and Machine Intelligence
IEEE Transactions on Pattern Analysis and Machine Intelligence
Multilingual machine printed OCR
Hidden Markov models
A Model of Unconstrained Digit Recognition Based on Hypothesis Testing and Data Reconstruction
AI '01 Proceedings of the 14th Australian Joint Conference on Artificial Intelligence: Advances in Artificial Intelligence
Word recognition system using neural networks
Highly parallel computaions
Telematics enabled virtual simulation system for radiation treatment planning
Computers in Biology and Medicine
SACH'06 Proceedings of the 2006 conference on Arabic and Chinese handwriting recognition
Cognitive hierarchical active partitions using patch approach
ICCVG'10 Proceedings of the 2010 international conference on Computer vision and graphics: Part I
Graph transformation in document image analysis: approaches and challenges
GbRPR'05 Proceedings of the 5th IAPR international conference on Graph-Based Representations in Pattern Recognition
Hi-index | 0.14 |
A segmentation-free approach to OCR is presented as part of a knowledge-based word interpretation model. This new method is based on the recognition of subgraphs homeomorphic to previously defined prototypes of characters [16]. Gaps are identified as potential parts of characters by implementing a variant of the notion of relative neighborhood used in computational perception. In the system, each subgraph of strokes that matches a previously defined character prototype is recognized anywhere in the word even if it corresponds to a broken character or to a character touching another one. The characters are detected in the order defined by the matching quality. Each subgraph that is recognized is introduced as a node in a directed net that compiles different alternatives of interpretation of the features in the feature graph. A path in the net represents a consistent succession of characters in the word. The method allows the recognition of characters that overlap or that are underlined. A final search for the optimal path under certain criteria gives the best interpretation of the word features. The character recognizer uses a flexible matching between the features and a flexible grouping of the individual features to be matched. Broken characters are recognized be looking for gaps between features that may be interpreted as part of a character. Touching characters are recognized because the matching allows nonmatched adjacent strokes. The recognition results of this system for over 24,000 printed numeral characters belonging to a USPS database and on some hand-printed words confirmed the method驴s high robustness level.