Document Analysis Systems VII

Inhaltsverzeichnis

• Session 1: Digital Libraries.
• Retrieval from Document Image Collections.
• A Semi-automatic Adaptive OCR for Digital Libraries.
• Session 2: Image Processing.
• Contribution to the Discrimination of the Medieval Manuscript Texts: Application in the Palaeography.
• Restoring Ink Bleed-Through Degraded Document Images Using a Recursive Unsupervised Classification Technique.
• Networked Document Imaging with Normalization and Optimization.
• Gray-Scale Thinning Algorithm Using Local Min/Max Operations.
• Session 3: Handwriting 1.
• Automated Scoring of Handwritten Essays Based on Latent Semantic Analysis.
• Aligning Transcripts to Automatically Segmented Handwritten Manuscripts.
• Virtual Example Synthesis Based on PCA for Off-Line Handwritten Character Recognition.
• Extraction of Handwritten Text from Carbon Copy Medical Form Images.
• Session 4: Document Structure and Format.
• Document Logical Structure Analysis Based on Perceptive Cycles.
• A System for Converting PDF Documents into Structured XML Format.
• XCDF: A Canonical and Structured Document Format.
• Structural Analysis of Mathematical Formulae with Verification Based on Formula Description Grammar.
• Session 5: Tables.
• Notes on Contemporary Table Recognition.
• Handwritten Artefact Identification Method for Table Interpretation with Little Use of Previous Knowledge.
• Session 6: Handwriting 2.
• Writer Identification for Smart Meeting Room Systems.
• Extraction and Analysis of Document Examiner Features from Vector Skeletons of Grapheme ‘th’.
• Segmentation of On-Line Handwritten Japanese Text Using SVM for Improving Text Recognition.
• Application of Bi-gram Driven Chinese Handwritten Character Segmentation for an Address Reading System.
• Session 7: Language and Script Identification.
• Language Identification in Degraded and Distorted Document Images.
• Bangla/English Script Identification Based on Analysis of Connected Component Profiles.
• Script Identification from Indian Documents.
• Finding the Best-Fit Bounding-Boxes.
• Session 9: Systems and Performance Evaluation.
• Towards Versatile Document Analysis Systems.
• Exploratory Analysis System for Semi-structured Engineering Logs.
• Ground Truth for Layout Analysis Performance Evaluation.
• On Benchmarking of Invoice Analysis Systems.
• Semi-automatic Ground Truth Generation for Chart Image Recognition.
• Session 10: Retrieval and Segmentation.
• Efficient Word Retrieval by Means of SOM Clustering and PCA.
• The Effects of OCR Error on the Extraction of Private Information.
• Combining Multiple Classifiers for Faster Optical Character Recognition.
• Performance Comparison of Six Algorithms for Page Segmentation.
• Posters.
• HVS Inspired System for Script Identification in Indian Multi-script Documents.
• A Shared Fragments Analysis System for Large Collections of Web Pages.
• Offline Handwritten Arabic Character Segmentation with Probabilistic Model.
• Automatic Keyword Extraction from Historical Document Images.
• Digitizing a Million Books: Challenges for Document Analysis.
• Toward File Consolidation by Document Categorization.
• Finding Hidden Semantics of Text Tables.
• Reconstruction of Orthogonal Polygonal Lines.
• A Multiclass Classification Framework for Document Categorization.
• The Restoration of Camera Documents Through Image Segmentation.
• Cut Digits Classification with k-NN Multi-specialist.
• The Impact of OCR Accuracy and Feature Transformation on Automatic Text Classification.
• A Method for Symbol Spotting in Graphical Documents.
• Groove Extraction of Phonographic Records.
• Use of Affine Invariants in Locally Likely Arrangement Hashing for Camera-Based Document Image Retrieval.
• Robust Chinese Character Recognition by Selection of Binary-Based and Grayscale-Based Classifier.
• Segmentation-Driven Recognition Applied to Numerical Field Extraction from Handwritten Incoming Mail Documents.
• Performance Evaluation of Text Detection and Tracking in Video.
• Document Analysis System for Automating Workflows.
• Automatic Assembling of Cadastral Maps Based on Generalized Hough Transformation.
• A Few Steps Towards On-the-Fly Symbol Recognition with Relevance Feedback.
• The Fuzzy-Spatial Descriptor for the Online Graphic Recognition: Overlapping Matrix Algorithm.