Vitorino Ramos: Automatic Feature Extraction and Recognition for Digital access of Books of the Renaissance

30. F. Muge, I. Granado, M. Mengucci, P. Pina, V. Ramos, N. Sirakov, J.R. Caldas Pinto, A. Marcolino, Mário Ramalho, P. Vieira, A. Maia do Amaral, Automatic Feature Extraction and Recognition for Digital Access of Books of the Renaissance, Proc. of ECDL'´000 - 4th European Conference on Research and Advanced Technology for Digital Libraries, J. Borbinha and T. Baker (Eds.), ISBN 3-540-41023-6, Lecture Notes in Computer Science, Vol. 1923, pp. 1-13, Springer-Verlag, Heidelberg, Lisbon, Portugal, 18-20 Sep. 2000.

Vitorino Ramos - Automatic Feature Extraction, Document Image Analysis and Pattern Recognition

Vitorino Ramos - Automatic Feature Extraction, Document Image Analysis and Pattern Recognition

Figures - Example of separation of text from non-text in a page of Os Lusiadas book (Luis de Camões - 1572). Check also this media article at Visão Magazine (in Portuguese).

Abstract: Antique printed books constitute a heritage that should be preserved and used. With novel digitising techniques is now possible to have these books stored in digital format and accessible to a wider public. However it remains the problem of how to use them. DEBORA (Digital accEss to BOoks of the RenAissance) is a European project that aims to develop a system to interact with these books through worldwide networks. The main issue is to build a database accessible through client computers. That will require to built accompanying metadata that should characterise different components of the books as illuminated letters, banners, figures and key words in order to simplify and speed up the remote access. To solve these problems, digital image analysis algorithms regarding filtering, segmentation, separation of text from non-text, lines and word segmentation and word recognition were developed. Some novel ideas are presented and illustrated through examples.

Keywords: Word matching, Textual Image Analysis, Classification, Image Processing, Image Segmentation, Mathematical Morphology, Document Mining.

Cited by:

º J.R.C. Pinto, P. Pina, L. Bandeira, L. Pimentel and M. Ramalho, "Underline Removal on Old Documents", in Image Analysis and Recognition, LNCS, Vol. 3212, pp. 226-233, Springer, 2004.

º Dimosthenis A. Karatzas, "Text Segmentation in Web Images Using Colour Perception and Topological Features", Phd Thesis, University of Liverpool, UK, 2003.

º Valguima V.V.A., Odakura Martinez, Geraldo Lino de Campos; "Image Registration of Ancient Documents", IKE´02 - International Conference on Information and Knowledge Engineering - Las Vegas, June 2002.

º Claudia Niederée, "Personalisierung, Kooperation und Evolution in digitalen Bibliotheken", PhD Dissertation, Technischen Universitat Hamburg-Harburg, Hamburg, Germany, June 2002.

º Valguima V.V.A., Odakura Martinez, Geraldo Lino de Campos; "Uma Técnica para Alinhamento de Imagens de Documentos Antigos", CSBC´02 - Anais do XII Congresso da Sociedade Brasileira de Computação, Florianópolis, Julho 2002.

º Isabel Granado, Pina. P., Muge F., Automatic Feature Extraction on pages of Antique Books through a Mathematical Morphology based Methodology, Proc. 10th Portuguese Conf. on Computer Graphics, ISCTE, Lisbon, Oct. 1-3, 2001.

º Caldas Pinto J., Marcolino A., Ramalho M., Muge F., Sirakov N. and Pina P., Comparing Matching Properties for Renaissance Printed Words, Proc. 10th Portuguese Conf. on Computer Graphics, ISCTE, Lisbon, Oct. 1-3, 2001.

31. Map Segmentation by Colour Cube Genetic K-Mean Clustering.

51. Evolving a Stigmergic Self-Organized Data-Mining.

55. Exploiting and Evolving Rⁿ Mathematical Morphology Feature Spaces.

29. Artificial Ant Colonies in Digital Image Habitats - A Mass Behaviour Effect Study on Pattern Recognition.

63. Social Cognitive Maps, Swarm Collective Perception and Distributed Search on Dynamic Landscapes.

45. Swarms on Continuous Data.