Tools

Aletheia

An Advanced Document Layout and Text Ground-Truthing System for Production Environments

Terms & Conditions

Aletheia is a systems that offers:

• System Features

  • Mature XML schema which is part of the PAGE format framework

  • Targets production environments (large scale digitisation)

• Built-in Operations

  • Image Binarisation

  • Noise Removal

  • Automatic Layout Analysis and OCR (using Tesseract OCR Engine v 3.02)

• Ground Truth Production

  • Border and Print Space

  • Layout Regions

  • Modification of Layout Regions (merge, split, edit outline)

  • Region Attributes

  • Text Content (Unicode with virtual keyboard for special characters)

  • Reading Order

  • Layers

  • Text Lines, Words and Glyphs also with text content

  • Validation against Ground Truthing Rules and Guidlines

Relevant Publication(s)

Aletheia - An Advanced Document Layout and Text Ground-Truthing System for Production Environments

C. Clausner, S. Pletschacher, A. Antonacopoulos

Proceedings of the 11th International Conference on Document Analysis and Recognition (ICDAR2011), Beijing, China, September 2011, pp. 48-52

[ further details]   [ full paper]

PAGE Libraries

A Java PAGE Library ready to be Integrated in your System

Terms & Conditions

The Java PAGE Library is a comprehensive set of Java classes that can be easily integrated to produce valid PAGE instances from within your tool.

A C++ PAGE Exporter ready to be Integrated in your System

Terms & Conditions

The C++ PAGE Exporter is a basic C++ class that can be easily integrated to produce valid PAGE instances from within your tool.

PAGE XML-schema

Alternatively you can produce PAGE files using your own XML library, following the PAGE Schema which can be found at: http://schema.primaresearch.org/PAGE/gts/pagecontent/2010-03-19/pagecontent.xsd.

Relevant Publication(s)

The PAGE (Page Analysis and Ground-Truth Elements) Format Framework

S. Pletschacher, A. Antonacopoulos

Proceedings of the 20th International Conference on Pattern Recognition (ICPR2010), Istanbul, Turkey, August 23-26, 2010, IEEE‐CS Press, pp. 257-260.

[ further details]   [ full paper]

Layout Evaluation

Scenario Driven In-Depth Performance Evaluation of Document Layout Analysis Methods

Terms & Conditions

Layout Evaluation is used to measure the performance of layout analysis systems and identify specific problems by comparing their results against ground truth data.

The tool comprises among other features:

• Evaluation Profile editor with Novel Metrics

• Fully customisable metrics for different Region Types (Text, Image, Table, ...)

• Fully customisable metrics for different Error Types (Merge, Split, Miss, Partial Miss, False Detection and Missclassification)

• All possible combinations of Region Types and Error Types can be defined

• Support for Reading Order (using boh ordered and unordered groups)

• Evaluation result viewer, featuring:

  • Colour and pattern coded, interactive overlay on the document image

  • Highlights segmentation and classification errors

Relevant Publication(s)

Scenario Driven In-Depth Performance Evaluation of Document Layout Analysis Methods

C. Clausner, S. Pletschacher, A. Antonacopoulos

Proceedings of the 11th International Conference on Document Analysis and Recognition (ICDAR2011), Beijing, China, September 2011, pp. 1404-1408

[ further details]   [ full paper]

For any enquires about our tools, please contact support@primaresearch.org