Development of a database with ground truth for old documents analysis

Abstract

Standard databases play essential roles for evaluating and comparing results obtained by different groups of researchers. In this paper, a database of images derived from the Tunisian heritage is introduced. We present first the importance of digitization for the preservation and the protection of patrimonial collections. Then, we describe the development process of our database, intended for the analysis of historical document images, in collaboration with the National Archives of Tunisia. In the second place, we demonstrate the importance of the ground truth for image databases and the annotation impact of these images. Thus, we present our approach for images annotation which consists in producing manually and collectively keywords for each image.

Image Extracting from Ancient Arab Documents with Complex Structures

“…This database consists of 700 newspaper pages characterized by a great structure variability and content richness. The considered documents are in grayscales with variable sizes, scanned at a resolution of 300 dpi in format "JPEG" and cover the majority of historical document problems [26].…”

Semi-automatic news video annotation framework for Arabic text

“…Analysis of Arabic documents and recognition/indexing of Arabic text actually became an attracting research domain in the recent years [4,5,6,7]. Major contributions have already been made in the field of printed and handwritten Arabic text data sets and OCR systems [4,6,8,9,10,11].…”