Back to search

Democritus University of Thrace (DUTH)

Αποκατάσταση ψηφιακών εγγράφων και εικόνων

Abstract

dc:description

The purpose of the doctoral dissertation is the development of novel techniques in the field of document and image restoration. Documents and images face numerous degradations, due to antiquity or through the process of digitization. As a result, there many techniques in literature that handle different sorts of problems. The major interest and the utility of restoration problems in real life were the best motives for the elaboration of proposed doctoral dissertation. Five techniques have been developed and implemented through the proposed doctoral dissertation. Each technique faces common and interesting problems in this scientific field, such as binarization of degraded documents, local and global skew detection, line, word and character segmentation, text localization in cover books and digital puzzle solving. § The proposed technique focuses on degraded documents with various background patterns and noise. It involves a pre-processing local background estimation stage, where the estimated background is used to produce a new enhanced image having uniform background layers and increased local contrast. That is, the new image is a combination of background and foreground layers. Foreground and background layers are then separated by using a new transformation which exploits efficiently, both gray-scale and spatial information. The final binary document is obtained by combining all foreground layers. § The second technique detects and restores global and local skew in complex color documents. The proposed technique consists of four main stages, which are, color reduction, text localization, document binarization and skew correction. Color reduction limits the initial number of colors to a small number. Text localization initially divides the document to a number of binary planes (color planes) equal to the number of the reduced colors. Then, connected component analysis is performed and text is extracted according to similarity features between adjacent connected components. In the third stage the binary document is composed by the processed binary planes. Finally, skew correction is achieved by detecting the direction of connection of the connected components in the binary images. § The proposed third technique segments document pages resulting from the digitization of historical machine-printed sources. This kind of documents often suffer from low quality and local skew, several degradations due to the old printing matrix quality or ink diffusion, and exhibit complex and dense layout. A novel Adaptive Run Length Smoothing Algorithm (ARLSA) is developed in this technique, in order to face the problem of complex and dense document layout. ARLSA performs much better than classical RLSA. Experimental results prove that the proposed technique performs better than state-of-the-art techniques. § Fourth technique performs text extraction in complex color documents and cover books. The number of colors of each document image is reduced into a relative small number (usually below ten colors) and each document is divided into binary images. Then, connected component analysis is performed and homogenous groups of connected components (CCs) are created. A set of features is extracted for each group. Finally, each group is classified into text or non-text class using a neuro-fuzzy classifier. § Last technique is developed for solving jigsaw puzzles. The novelty of the proposed technique is that it provides an automatic jigsaw puzzle solution without any initial restriction about the shape of pieces, the number neighbor pieces etc. The proposed technique uses both curve and color matching similarity features. A recurrent procedure is applied, which compares and merges puzzle pieces in pairs, until the original puzzle image is reformed. Geometrical and color features are extracted on characteristic points of the puzzle pieces.

Degree

thesis:*
Grantor dc:publisher
Democritus University of Thrace (DUTH)
Year dc:date
2010

Author and committee

dc:creator, dc:contributor.*
Authors dc:creator
  • Makridis, Michael
  • Μακρίδης, Μιχαήλ

Subjects

dc:subject × 17

Rights

Language dc:language
gre

Identifiers

dc:identifier.*
Identifier
10.12681/eadd/20839

Chain of custody

source
Harvested from
Greek National Archive of PhD Theses
Base URL
phdtheses.ekt.gr/eadd_oai/request
Last updated
2026-11-18
Source record
OAI-PMH GetRecord
citation

Makridis, Michael; Μακρίδης, Μιχαήλ. Αποκατάσταση ψηφιακών εγγράφων και εικόνων. Democritus University of Thrace (DUTH), 2010. http://hdl.handle.net/10442/hedi/20839