Combining Morphological and Histogram based Text Line Segmentation in the OCR Context

Text line segmentation is one of the pre-stages of modern optical character recognition systems. The algorithmic approach proposed by this paper has been designed for this exact purpose. Its main characteristic is the combination of two different techniques, morphological image operations and horizontal histogram projections. The method was developed to be applied on a historic data collection that commonly features quality issues, such as degraded paper, blurred text, or presence of noise. For that reason, the segmenter in question could be of particular interest for cultural institutions, that want access to robust line bounding boxes for a given historic document. Because of the promising segmentation results that are joined by low computational cost, the algorithm was incorporated into the OCR pipeline of the National Library of Luxembourg, in the context of the initiative of reprocessing their historic newspaper collection. The general contribution of this paper is to outline the approach and to evaluate the gains in terms of accuracy and speed, comparing it to the segmentation algorithm bundled with the used open source OCR software.

Ficção e fruição de paisagens de Oitocentos: entre o Porto e Vila Real, por Edward Quillinan

The Edward Quillinan’s novel The Sisters of the Douro highlights a set of Heritage Lands‑ capes confined by the banks of the Douro river, as well as all the anthropic process about customs and manners of the Douro inhabitants during the 2nd French invasion of northern Portugal. On the narrative stage between Porto and Vila Real, the text is deeply enriched by heritages of urban or country landscapes observed along the way, describing building and topographic details, includ‑ ing flora and fauna. Imposed by the romantic literary aesthetics, the reader also notices about a loving plot of two Portuguese young women from the Douro and two English officers, pages where deep and original cultural and anthropic perspectives are developed. This novel is generally consi‑ dered a historic document of the Portuguese Patrimony of the nineteenth century. For this reason, and in accordance with the cultural and geographical framework provided by literary realism, it is acceptable that all those heritage values can be prospectively collected and considered

Where is the authenticity of the contemporary art?

In the contemporary art, the conservation of the original matter is not as important as the conservation of the authenticity of the work, because of this it is very important to know the artist and his work, to be able to conserve the most important values. In this process it is very important the documentation and the research. Therefore the criteria of restoration has changed, we can not conserve the patina of the contemporary art as a historic document, if this means the loss of the aesthetic value of the work. Nowadays the art is different, and therefore its conservation is different too.