A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf
.
Filters
A texture-based pixel labeling approach for historical books
2015
Pattern Analysis and Applications
The novelty of this work lies in the clustering of extracted texture descriptors to find automatically homogeneous regions, i.e. graphic and textual regions, by using the clustering approach on an entire ...
One important challenge is to refine well-known approaches based on strong a priori knowledge (e.g. the document image content, layout, typography, font size and type, scanning resolution, image size, ...
Our goal is to extract as automatically as possible textural features that segment an ancient book or a collection of historical documents into spatially disjoint homogeneous regions or similar content ...
doi:10.1007/s10044-015-0451-9
fatcat:b5njvrjrzjf75iq4t6lvzbqu2m
Historical Document Analysis: A Review Of French Projects And Open Issues
2011
Zenodo
Indexing on Graphical Features Usually, documents are indexed mainly on text. ...
For graphics in old manuscripts, some new signatures have to be developed in order to order offer hyper-text navigation based on meta-data obtained using word spotting or graphic spotting methods (see ...
doi:10.5281/zenodo.42437
fatcat:7wm5pday6ngetldtnej2xbi52a
Use of SLIC superpixels for ancient document image enhancement and segmentation
2015
Document Recognition and Retrieval XXII
Firstly, in order to obtain enhanced backgrounds of noisy ancient documents, a novel foreground/background segmentation algorithm based on SLIC superpixels, is introduced. ...
Thus, we propose in this article a fast ancient document enhancement and segmentation algorithm based on using Simple Linear Iterative Clustering (SLIC) superpixels and Gabor descriptors in a multi-scale ...
Figure (a) illustrates an example of an ancient document containing graphics and one text font. Figure (b) shows an example of an ancient document containing only two text fonts. ...
doi:10.1117/12.2076020
dblp:conf/drr/MehriSHGAM15
fatcat:xxreddbarrbufdstjrvrawgcb4
Learning-Based Ordering Characters on Ancient Document
2022
Computational Intelligence and Neuroscience
We offer the ground truth assign method based on the absolute position to assign similar indexes to characters in similar places. ...
The network must learn to give various indexes to characters in similar places for each document because the number and area of characters vary for each document. ...
Tis result is similar to the index ED trend (human � 14.88, RIF � 9.79, GIF � 6.40, and GIF + RIF � 6.73) of documents that have split lines into two on ancient documents, and it is also similar to the ...
doi:10.1155/2022/3260384
pmid:36438692
pmcid:PMC9691315
fatcat:v75g5dgesrd5phdxtixqbe4jjq
A Pixel Labeling Framework for Comparing Texture Features Application to Digitized Ancient Books
english
2014
Proceedings of the 3rd International Conference on Pattern Recognition Applications and Methods
english
Firstly, the content of an entire book is characterized by extracting the texture attributes of each page. The extraction of the texture features is based on a multiresolution analysis. ...
Namely, two approaches are compared based on two different statistical categories of texture features, autocorrelation and co-occurrence, in order to segment the content of ancient book pages and find ...
., 2008) proposed to characterize and index images of ancient documents by their content by exploring textural analysis based on statistical and spectral properties of texture. ...
doi:10.5220/0004804705530560
dblp:conf/icpram/MehriGHBM14
fatcat:enol45hphvfs7itjl6jkogm7rm
Texture feature evaluation for segmentation of historical document images
2013
Proceedings of the 2nd International Workshop on Historical Document Imaging and Processing - HIP '13
Texture feature evaluation for segmentation of historical document images. ...
They are related to the desire for a quicker analysis, indexing, and retrieval of the scanned documents as well as an increase of the life time of ancient books. ...
[12] demonstrate the effectiveness of a texture-based segmentation method for a variety of document image processing issues: text-graphics separation, address-block location, etc. ...
doi:10.1145/2501115.2501121
dblp:conf/icdar/MehriGHBM13
fatcat:bi2jw5weazbo5fws7ryvhepiiu
A Survey on Document Image Analysis and Retrieval System
2015
International Journal on Cybernetics & Informatics
The digitization of documents and their availability over the network demands solution toward content based document image analysis, indexing, searching and retrieval. ...
Signature, Logo and Layout of the documents present convincing evidence and provide an important form of indexing for effective document image retrieval in a variety of applications. ...
of indexing the documents and is based on signature, layout and logos. ...
doi:10.5121/ijci.2015.4225
fatcat:qy5zdi2mmfgqhjoa5qreq3rr7q
Robustness Assessment of Texture Features for the Segmentation of Ancient Documents
2014
2014 11th IAPR International Workshop on Document Analysis Systems
In addition, it has been proven that the texture-based approaches work effectively without hypothesis on the document structure, neither on the document model nor the typographical parameters. ...
Thus, by investigating the use of texture as a tool for automatically segmenting images, we propose to search homogeneous and similar content regions by analyzing texture features based on a multiresolution ...
comparison, and indexing of ancient digitized books collected from the Gallica digital library 2 . ...
doi:10.1109/das.2014.22
dblp:conf/das/MehriKMHGMM14
fatcat:itg2xllne5cmnbo5jzr7ng6ote
Learning Texture Features for Enhancement and Segmentation of Historical Document Images
2015
Proceedings of the 3rd International Workshop on Historical Document Imaging and Processing - HIP '15
Thus, the performance of a Gabor-based method depends directly on the layout document. ...
EXPERIMENTS We have experimentally evaluated the proposed ancient document enhancement and segmentation algorithm on 100 pages of ancient documents. ...
doi:10.1145/2809544.2809545
dblp:conf/icdar/MehriNHGM15
fatcat:nuztk7z7m5eqjeb7yoxk3r7qni
An Image Based Approach for Content Analysis in Document Collections
[chapter]
2013
Lecture Notes in Computer Science
In order to incorporate spatial information into the bag of features approach we consider three methods of spatial verification. ...
An approach based on comparison of statistical properties of local keypoint properties such as size orientation and scale showed comparable quality in content comparison while being computationally much ...
The authors would like to thank Sven Schlarb from the Austrian National Library (ONB) for providing data and expertise on library workflows. ...
doi:10.1007/978-3-642-41939-3_27
fatcat:vrb2pqj6czdhlod5sksuszkpha
A bottom-up method using texture features and a graph-based representation for lettrine recognition and classification
2015
2015 13th International Conference on Document Analysis and Recognition (ICDAR)
Firstly, we propose a bottom-up segmentation method, based on texture, ensuring the separation of the letter from the elements of the background in an ornamental letter. ...
This article tackles some important issues relating to the analysis of a particular case of complex ancient graphic images, called "lettrines", "drop caps" or "ornamental letters". ...
The main goals of these projects are to provide a computer-based access and analysis of cultural heritage documents, searchable and browseable historical document image databases, and an automatic indexing ...
doi:10.1109/icdar.2015.7333757
dblp:conf/icdar/MehriGHCLM15
fatcat:dxjbbtbb3rb3td2u5y3qqjz3la
Extraction of Homogeneous Regions in Historical Document Images
2015
Proceedings of the 10th International Conference on Computer Vision Theory and Applications
Thus, we propose in this article an automatic segmentation method for historical document images based on extraction of homogeneous or similar content regions. ...
To reach the objective of ensuring the indexing and retrieval of digitized resources and offering a structured access to large sets of cultural heritage documents, a raising interest to historical document ...
between different graphic types in HDIs, an automatic segmentation method for HDIs based on extraction of homogeneous or similar content regions is proposed in this article. ...
doi:10.5220/0005265500470054
dblp:conf/visapp/MehriHSGAM15
fatcat:z4dhhtjvuzfj5hiukasqi5nelu
Text graphic separation in Indian newspapers
2013
Proceedings of the 4th International Workshop on Multilingual OCR - MOCR '13
The learning problem has been formulated as an optimization problem using EM algorithm to learn optimal parameters depending on the nature of the document content. ...
In this paper we propose a novel framework for learning optimal parameters for text graphic separation in the presence of complex layouts. ...
An EM based estimation framework has been formulated to learn parameters based on the nature of the document image content. ...
doi:10.1145/2505377.2505393
dblp:conf/icdar/GargBCR13
fatcat:f6pnvpn2rnh5tbxlotbsaxid64
A Method for Image Local-Difference Visualization
2007
Proceedings of the International Conference on Document Analysis and Recognition
As ancient documents are being digitized, systems for retrieving documents or images can now be found in Digital Libraries. ...
We propose here a method that evaluates locally the differences and allows the user to visualize them. It is based on a local adaptation of the Hausdorff distance. ...
Introduction This article addresses visualization of differences for ancient-document graphical parts. ...
doi:10.1109/icdar.2007.4377055
dblp:conf/icdar/BaudrierR07
fatcat:qvumnqb4xbb3dlakiwtkjn55pm
An integrated reading and editing environment for scholarly research on literary works and their handwritten sources
1998
Proceedings of the third ACM conference on Digital libraries - DL '98
A semi-automatic system based on computer-human interaction and document analysis is proposed for performing this task. ...
We present an integrated system devoted to the visualization and the editing of hypermedia documents from literary material including document images and structured text. ...
While being easy to read and lending themselves to easy computerized manipulation, these text-based representations are not very good at recording the graphical features of ancient documents. ...
doi:10.1145/276675.276691
dblp:conf/dl/LecolinetLRRL98
fatcat:b2jrummwvveubmwqpeg2hpic3i
« Previous
Showing results 1 — 15 out of 9,318 results