Automatic digital document processing and management: problems, algorithms and techniques

Description

Machine generated contents note: pt. I Digital Documents -- 1. Documents -- 1.1. Juridic Perspective -- 1.2. History and Trends -- 1.3. Current Landscape -- 1.4. Types of Documents -- 1.5. Document-Based Environments -- 1.6. Document Processing Needs -- References -- 2. Digital Formats -- 2.1. Compression Techniques -- RLE (Run Length Encoding) -- Huffman Encoding -- LZ77 and LZ78 (Lempel-Ziv) -- LZW (Lempel-Ziv-Welch) -- DEFLATE -- 2.2. Non-structured Formats -- 2.2.1. Plain Text -- ASCII -- ISO Latin -- UNICODE -- UTF -- 2.2.2. Images -- Color Spaces -- RGB -- YUV/YCbCr -- CMY(K) -- HSV/HSB and HLS -- Comparison among Color Spaces -- Raster Graphics -- BMP (BitMaP) -- GIF (Graphics Interchange Format) -- TIFF (Tagged Image File Format) -- JPEG (Joint Photographic Experts Group) -- PNG (Portable Network Graphics) -- DjVu (DejaVu) -- Vector Graphic -- SVG (Scalable Vector Graphic) -- 2.3. Layout-Based Formats -- PS (PostScript) -- PDF (Portable Document Format) -- 2.4. Content-Oriented Formats -- 2.4.1. Tag-Based Formats -- HTML (HyperText Markup Language) -- XML (extensible Markup Language) -- 2.4.2. Office Formats -- ODF (OpenDocument Format) -- References -- 3. Legal and Security Aspects -- 3.1. Cryptography -- 3.1.1. Basics -- 3.1.2. Short History -- 3.1.3. Digital Cryptography -- DES (Data Encryption Standard) -- IDEA (International Data Encryption Algorithm) -- Key Exchange Method -- RSA (Rivest, Shamir, Adleman) -- DSA (Digital Signature Algorithm) -- 3.2. Message Fingerprint -- SHA (Secure Hash Algorithm) -- 3.3. Digital Signature -- 3.3.1. Management -- DSS (Digital Signature Standard) -- OpenPGP Standard -- 3.3.2. Trusting and Certificates -- 3.4. Legal Aspects -- 3.4.1. Law Approach -- 3.4.2. Public Administration Initiatives -- Digital Signature -- Certified e-mail -- Electronic Identity Card & National Services Card -- Telematic Civil Proceedings -- References -- pt. II Document Analysis -- 4. Image Processing -- 4.1. Basics -- Convolution and Correlation -- 4.2. Color Representation -- 4.2.1. Color Space Conversions -- RGB-YUV -- RGB-YCbCr -- RGB-CMY(K) -- RGB-HSV -- RGB-HLS -- 4.2.2. Colorimetric Color Spaces -- XYZ -- Lab -- 4.3. Color Depth Reduction -- 4.3.1. Desaturation -- 4.3.2. Grayscale (Luminance) -- 4.3.3. Black&White (Binarization) -- Otsu Thresholding -- 4.4. Content Processing -- 4.4.1. Geometrical Transformations -- 4.4.2. Edge Enhancement -- Derivative Filters -- 4.4.3. Connectivity -- Flood Filling -- Border Following -- Dilation and Erosion -- Opening and Closing -- 4.5. Edge Detection -- Canny -- Hough Transform -- Polygonal Approximation -- Snakes -- References -- 5. Document Image Analysis -- 5.1. Document Structures -- 5.1.1. Spatial Description -- 4-Intersection Model -- Minimum Bounding Rectangles -- 5.1.2. Logical Structure Description -- DOM (Document Object Model) -- 5.2. Pre-processing for Digitized Documents -- Document Image Defect Models -- 5.2.1. Deskewing -- 5.2.2. Dewarping -- Segmentation-Based Dewarping -- 5.2.3. Content Identification -- 5.2.4. Optical Character Recognition -- Tesseract -- JTOCR -- 5.3. Segmentation -- 5.3.1. Classification of Segmentation Techniques -- 5.3.2. Pixel-Based Segmentation -- RLSA (Run Length Smoothing Algorithm) -- RLSO (Run-Length Smoothing with OR) -- X-Y Trees -- 5.3.3. Block-Based Segmentation -- DOCSTRUM -- CLiDE (Chemical Literature Data Extraction) Approach -- Background Analysis -- RLSO on Born-Digital Documents -- 5.4. Document Image Understanding -- 5.4.1. Relational Approach -- INTHELEX (INcremental THEory Learner from Examples) -- 5.4.2. Description -- DCMI (Dublin Core Metadata Initiative) -- References -- pt. III Content Processing -- 6. Natural Language Processing -- 6.1. Resources -- Lexical Taxonomies -- WordNet -- WordNet Domains -- Senso Comune -- 6.2. Tools -- 6.2.1. Tokenization -- 6.2.2. Language Recognition -- 6.2.3. Stopword Removal -- 6.2.4. Stemming -- Suffix Stripping -- 6.2.5. Part-of-Speech Tagging -- Rule-Based Approach -- 6.2.6. Word Sense Disambiguation -- Lesk's Algorithm -- Yarowsky's Algorithm -- 6.2.7. Parsing -- Link Grammar -- References -- 7. Information Management -- 7.1. Information Retrieval -- 7.1.1. Performance Evaluation -- 7.1.2. Indexing Techniques -- Vector Space Model -- 7.1.3. Query Evaluation -- Relevance Feedback -- 7.1.4. Dimensionality Reduction -- Latent Semantic Analysis and Indexing -- Concept Indexing -- 7.1.5. Image Retrieval -- 7.2. Key word Extraction -- TF-ITP -- Naive Bayes -- Co-occurrence -- 7.3. Text Categorization -- Semantic Approach Based on WordNet Domains -- 7.4. Information Extraction -- WHISK -- Multistrategy Approach -- 7.5. Semantic Web -- References -- Appendix A Case Study: DOMINUS -- A.1. General Framework -- A.1.1. Actors and Workflow -- A.1.2. Architecture -- A.2. Functionality -- A.2.1. Input Document Normalization -- A.2.2. Layout Analysis -- Kernel-Based Basic Blocks Grouping -- A.2.3. Document Image Understanding -- A.2.4. Categorization, Filing and Indexing -- A.3. Prototype Implementation -- A.4. Exploitation for Scientific Conference Management -- GRAPE -- Appendix B Machine Learning Notions -- B.1. Categorization of Techniques -- B.2. Noteworthy Techniques -- Artificial Neural Networks -- Decision Trees -- k-Nearest Neighbor -- Inductive Logic Programming -- Naive Bayes -- Hidden Markov Models -- Clustering -- B.3. Experimental Strategies -- k-Fold Cross-Validation -- Leave-One-Out -- Random Split -- Glossary -- Bounding box -- Byte ordering -- Ceiling function -- Chunk -- Connected component -- Heaviside unit function -- Heterarchy -- KL-divergence -- Linear regression -- Run -- Scanline.