Advances In Pattern Recognition - Icapr 2001: Second International Conference Rio De Janeiro, Brazil, March 11-14, 2001 Proceedings (lecture Notes In Computer Science)

The paper is organized as follows: In section 2, we describe the no- orientation-discontinuity interfering model based on a Gaussian stochastic model in analyzing the properties of the interfering strokes. In section 3, we describe the improved canny edge detector with an ed- orientation constraint to detect the edges and recover the weak ones of the foreground words and characters; In section 4, we illustrate, discuss and evaluate the experimental results of the proposed method, demonstrating that our algorithm significantly improves the segmentation quality; Section 5 concludes this paper. 2. The norm-orientation-discontinuity interfering stroke model Figure 2 shows three typical samples of original image segments from the original documents and their magnitude of the detected edges respectively. The magnitude of the gradient is converted into the gray level value. The darker the edge is, the larger is the gradient magnitude. It is obvious that the topmost strong edges correspond to foreground edges. It should be noted that, while usually, the foreground writing appears darker than the background image, as shown in sample image Figure 2(a), there are cases where the foreground and background have similar intensities as shown in Figure 2(b), or worst still, the background is more prominent than the foreground as in Figure 2(c). So using only the intensity value is not enough to differentiate the foreground from the background. (a) (b) (c) (d) (e) (f) Towards Bridging the Gap between Statistical and Structural Pattern Recognition: Two New Concepts in Graph Matching....Pages 1-11 Learning and Adaptation in Robotics....Pages 12-23 Image-based self-localization by means of zero phase representation in panoramic images....Pages 24-31 A Cascaded Genetic Algorithm for efficient optimization and pattern matching....Pages 32-39 Using Unlabelled Data to Train a Multilayer Perceptron....Pages 40-49 A Neural Multi -Expert Classification System for MPEG Audio Segmentation....Pages 50-59 Pattern Recognition with Quantum Neural Networks....Pages 60-71 Pattern Matching and Neural Networks based Hybrid Forecasting System....Pages 72-82 Invariant Face Detection in Color Images Using Orthogonal Fourier-Mellin Moments and Support Vector Machines....Pages 83-92 Character Extraction from Interfering Background - Analysis of Double-sided Handwritten Archival Documents....Pages 93-102 An Enhanced HMM Topology in an LBA Framework for the Recognition of Handwritten Numeral Strings....Pages 105-114 Segmentation of Printed Arabic Text....Pages 115-126 A Time—Length Constrained Level Building Algorithm for Large Vocabulary Handwritten Word Recognition....Pages 127-136 Preventing Overfitting in Learning Text Patterns for Document Categorization....Pages 137-146 Image Document Categorization using Hidden Tree Markov Models and Structured Representations....Pages 147-156 Handwriting Quality Evaluation....Pages 157-165 Texture Based Look-Ahead for Decision-Tree Induction....Pages 166-175 Feature Based Decision Fusion....Pages 176-185 Feature Selection Based on Fuzzy Distances Between Clusters: First Results on Simulated Data....Pages 186-195 Efficient and Effective Feature Selection in the Presence of Feature Interaction and Noise....Pages 196-204 Integrating Recognition Paradigms in a Multiple-path Architecture....Pages 205-213 A New Geometric Tool for Pattern Recognition - An Algorithm for Real Time Insertion of Layered Segment Trees....Pages 214-223 Improvements in K-Nearest Neighbor Classification....Pages 224-231 Branch & Bound Algorithm with Partial Prediction for Use with Recursive and Non-Recursive Criterion Forms....Pages 232-241 Model Validation for Model Selection....Pages 242-251 Grouping via the Matching of Repeated Patterns....Pages 252-261 Complex Fittings....Pages 262-271 Application of adaptive committee classifiers in on-line character recognition....Pages 272-281 Learning Complex Action Patterns with CRG ST ....Pages 282-291 Identification of electrical activity of the brain associated with changes in behavioural performance....Pages 292-302 Automatic Camera Calibration for Image Sequences of a Football Match....Pages 303-312 Locating and Tracking Facial Landmarks Using Gabor Wavelet Networks....Pages 313-322 Complex Images and Complex Filters: A Unified Model for Encoding and Matching Shape and Colour....Pages 323-332 White Matter/Gray Matter Boundary Segmentation Using Geometric Snakes: A Fuzzy Deformable Model....Pages 333-340 Multiseeded Fuzzy Segmentation on the Face Centered Cubic Grid....Pages 341-350 3D Wavelet based Video Retrieval....Pages 351-360 Combined Invariants to Convolution and Rotation and their Application to Image Registration....Pages 361-370 Modelling Plastic Distortion in Fingerprint Images....Pages 371-378 Image Retrieval Using a Hierarchy of Clusters....Pages 379-388 Texture-adaptive active contour models....Pages 389-398 A Generalized Local Binary Pattern Operator for Multiresolution Gray Scale and Rotation Invariant Texture Classification....Pages 399-408 Analysis of Curved Textured Surfaces Using Local Spectral Distortion....Pages 409-418 Texture Analysis Experiments with Meastex and Vistex Benchmarks....Pages 419-426 Advances in Statistical Feature Selection....Pages 427-436 Learning-Based Detection, Segmentation and Matching of Objects....Pages 437-446 Automated Biometrics....Pages 447-455

This book constitutes the refereed proceedings of the Second International Conference on Advances in Pattern Recognition, ICAPR 2001, held in Rio de Janeiro, Brazil in March 2001.
The 40 revised full papers presented together with three invited papers and two tutorial presentations were carefully reviewed and selected for inclusion in the proceedings. The book is organized in topical sections on neural networks and computational intelligence, character recognition and document analysis, feature selection and analysis, pattern recognition and classification, image and signal processing applications, and image feature analysis and retrieval.

Graphs are a flexible and powerful data structure for the representation of objects and concepts.