![Advances in Pattern Recognition — ICAPR 2001 [electronic resource] : Second International Conference Rio de Janeiro, Brazil, March 11–14, 2001 Proceedings /](/search/themes/bootstrap3/images/libros.png)
Advances in Pattern Recognition — ICAPR 2001 [electronic resource] : Second International Conference Rio de Janeiro, Brazil, March 11–14, 2001 Proceedings /
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).
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Texto biblioteca |
| Language: | eng |
| Published: |
Berlin, Heidelberg : Springer Berlin Heidelberg,
2001
|
| Subjects: | Computer science., Text processing (Computer science)., Computer graphics., Image processing., Pattern recognition., Computer Science., Pattern Recognition., Image Processing and Computer Vision., Computer Graphics., Document Preparation and Text Processing., |
| Online Access: | http://dx.doi.org/10.1007/3-540-44732-6 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| id |
KOHA-OAI-TEST:197125 |
|---|---|
| record_format |
koha |
| institution |
COLPOS |
| collection |
Koha |
| country |
México |
| countrycode |
MX |
| component |
Bibliográfico |
| access |
En linea En linea |
| databasecode |
cat-colpos |
| tag |
biblioteca |
| region |
America del Norte |
| libraryname |
Departamento de documentación y biblioteca de COLPOS |
| language |
eng |
| topic |
Computer science. Text processing (Computer science). Computer graphics. Image processing. Pattern recognition. Computer Science. Pattern Recognition. Image Processing and Computer Vision. Computer Graphics. Document Preparation and Text Processing. Computer science. Text processing (Computer science). Computer graphics. Image processing. Pattern recognition. Computer Science. Pattern Recognition. Image Processing and Computer Vision. Computer Graphics. Document Preparation and Text Processing. |
| spellingShingle |
Computer science. Text processing (Computer science). Computer graphics. Image processing. Pattern recognition. Computer Science. Pattern Recognition. Image Processing and Computer Vision. Computer Graphics. Document Preparation and Text Processing. Computer science. Text processing (Computer science). Computer graphics. Image processing. Pattern recognition. Computer Science. Pattern Recognition. Image Processing and Computer Vision. Computer Graphics. Document Preparation and Text Processing. Singh, Sameer. editor. Murshed, Nabeel. editor. Kropatsch, Walter. editor. SpringerLink (Online service) Advances in Pattern Recognition — ICAPR 2001 [electronic resource] : Second International Conference Rio de Janeiro, Brazil, March 11–14, 2001 Proceedings / |
| description |
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). |
| format |
Texto |
| topic_facet |
Computer science. Text processing (Computer science). Computer graphics. Image processing. Pattern recognition. Computer Science. Pattern Recognition. Image Processing and Computer Vision. Computer Graphics. Document Preparation and Text Processing. |
| author |
Singh, Sameer. editor. Murshed, Nabeel. editor. Kropatsch, Walter. editor. SpringerLink (Online service) |
| author_facet |
Singh, Sameer. editor. Murshed, Nabeel. editor. Kropatsch, Walter. editor. SpringerLink (Online service) |
| author_sort |
Singh, Sameer. editor. |
| title |
Advances in Pattern Recognition — ICAPR 2001 [electronic resource] : Second International Conference Rio de Janeiro, Brazil, March 11–14, 2001 Proceedings / |
| title_short |
Advances in Pattern Recognition — ICAPR 2001 [electronic resource] : Second International Conference Rio de Janeiro, Brazil, March 11–14, 2001 Proceedings / |
| title_full |
Advances in Pattern Recognition — ICAPR 2001 [electronic resource] : Second International Conference Rio de Janeiro, Brazil, March 11–14, 2001 Proceedings / |
| title_fullStr |
Advances in Pattern Recognition — ICAPR 2001 [electronic resource] : Second International Conference Rio de Janeiro, Brazil, March 11–14, 2001 Proceedings / |
| title_full_unstemmed |
Advances in Pattern Recognition — ICAPR 2001 [electronic resource] : Second International Conference Rio de Janeiro, Brazil, March 11–14, 2001 Proceedings / |
| title_sort |
advances in pattern recognition — icapr 2001 [electronic resource] : second international conference rio de janeiro, brazil, march 11–14, 2001 proceedings / |
| publisher |
Berlin, Heidelberg : Springer Berlin Heidelberg, |
| publishDate |
2001 |
| url |
http://dx.doi.org/10.1007/3-540-44732-6 |
| work_keys_str_mv |
AT singhsameereditor advancesinpatternrecognitionicapr2001electronicresourcesecondinternationalconferenceriodejaneirobrazilmarch11142001proceedings AT murshednabeeleditor advancesinpatternrecognitionicapr2001electronicresourcesecondinternationalconferenceriodejaneirobrazilmarch11142001proceedings AT kropatschwaltereditor advancesinpatternrecognitionicapr2001electronicresourcesecondinternationalconferenceriodejaneirobrazilmarch11142001proceedings AT springerlinkonlineservice advancesinpatternrecognitionicapr2001electronicresourcesecondinternationalconferenceriodejaneirobrazilmarch11142001proceedings |
| _version_ |
1756266973398827008 |
| spelling |
KOHA-OAI-TEST:1971252018-07-30T23:22:57ZAdvances in Pattern Recognition — ICAPR 2001 [electronic resource] : Second International Conference Rio de Janeiro, Brazil, March 11–14, 2001 Proceedings / Singh, Sameer. editor. Murshed, Nabeel. editor. Kropatsch, Walter. editor. SpringerLink (Online service) textBerlin, Heidelberg : Springer Berlin Heidelberg,2001.engThe 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).INVITED TALKS -- Towards Bridging the Gap between Statistical and Structural Pattern Recognition: Two New Concepts in Graph Matching -- Learning and Adaptation in Robotics -- Image-based self-localization by means of zero phase representation in panoramic images -- NEURAL NETWORKS & COMPUTATIONAL INTELLIGENCE -- A Cascaded Genetic Algorithm for efficient optimization and pattern matching -- Using Unlabelled Data to Train a Multilayer Perceptron -- A Neural Multi -Expert Classification System for MPEG Audio Segmentation -- Pattern Recognition with Quantum Neural Networks -- Pattern Matching and Neural Networks based Hybrid Forecasting System -- Invariant Face Detection in Color Images Using Orthogonal Fourier-Mellin Moments and Support Vector Machines -- CHARACTER RECOGNITION & DOCUMENT ANALYSIS -- Character Extraction from Interfering Background - Analysis of Double-sided Handwritten Archival Documents -- An Enhanced HMM Topology in an LBA Framework for the Recognition of Handwritten Numeral Strings -- Segmentation of Printed Arabic Text -- A Time—Length Constrained Level Building Algorithm for Large Vocabulary Handwritten Word Recognition -- Preventing Overfitting in Learning Text Patterns for Document Categorization -- Image Document Categorization using Hidden Tree Markov Models and Structured Representations -- Handwriting Quality Evaluation -- FEATURE SELECTION & ANALYSIS -- Texture Based Look-Ahead for Decision-Tree Induction -- Feature Based Decision Fusion -- Feature Selection Based on Fuzzy Distances Between Clusters: First Results on Simulated Data -- Efficient and Effective Feature Selection in the Presence of Feature Interaction and Noise -- Integrating Recognition Paradigms in a Multiple-path Architecture -- A New Geometric Tool for Pattern Recognition - An Algorithm for Real Time Insertion of Layered Segment Trees -- PATTERN RECOGNITION & CLASSIFICATION -- Improvements in K-Nearest Neighbor Classification -- Branch & Bound Algorithm with Partial Prediction for Use with Recursive and Non-Recursive Criterion Forms -- Model Validation for Model Selection -- Grouping via the Matching of Repeated Patterns -- Complex Fittings -- Application of adaptive committee classifiers in on-line character recognition -- Learning Complex Action Patterns with CRGST -- IMAGE & SIGNAL PROCESSING APPLICATIONS -- Identification of electrical activity of the brain associated with changes in behavioural performance -- Automatic Camera Calibration for Image Sequences of a Football Match -- Locating and Tracking Facial Landmarks Using Gabor Wavelet Networks -- Complex Images and Complex Filters: A Unified Model for Encoding and Matching Shape and Colour -- White Matter/Gray Matter Boundary Segmentation Using Geometric Snakes: A Fuzzy Deformable Model -- Multiseeded Fuzzy Segmentation on the Face Centered Cubic Grid -- IMAGE FEATURE ANALYSIS & RETRIEVAL -- 3D Wavelet based Video Retrieval -- Combined Invariants to Convolution and Rotation and their Application to Image Registration -- Modelling Plastic Distortion in Fingerprint Images -- Image Retrieval Using a Hierarchy of Clusters -- Texture-adaptive active contour models -- A Generalized Local Binary Pattern Operator for Multiresolution Gray Scale and Rotation Invariant Texture Classification -- Analysis of Curved Textured Surfaces Using Local Spectral Distortion -- Texture Analysis Experiments with Meastex and Vistex Benchmarks -- TUTORIALS -- Advances in Statistical Feature Selection -- Learning-Based Detection, Segmentation and Matching of Objects -- Automated Biometrics.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).Computer science.Text processing (Computer science).Computer graphics.Image processing.Pattern recognition.Computer Science.Pattern Recognition.Image Processing and Computer Vision.Computer Graphics.Document Preparation and Text Processing.Springer eBookshttp://dx.doi.org/10.1007/3-540-44732-6URN:ISBN:9783540447320 |