Browsing by Subject "Archives--Data processing."

Now showing 1 - 3 of 3

Open Access
Historical document analysis based on word matching
(2011) Arifoğlu, Damla
Historical documents constitute a heritage which should be preserved and providing automatic retrieval and indexing scheme for these archives would be beneficial for researchers from several disciplines and countries. Unfortunately, applying ordinary Optical Character Recognition (OCR) techniques on these documents is nearly impossible, since these documents are degraded and deformed. Recently, word matching methods are proposed to access these documents. In this thesis, two historical document analysis problems, word segmentation in historical documents and Islamic pattern matching in kufic images are tackled based on word matching. In the first task, a cross document word matching based approach is proposed to segment historical documents into words. A version of a document, in which word segmentation is easy, is used as a source data set and another version in a different writing style, which is more difficult to segment into words, is used as a target data set. The source data set is segmented into words by a simple method and extracted words are used as queries to be spotted in the target data set. Experiments on an Ottoman data set show that cross document word matching is a promising method to segment historical documents into words. In the second task, firstly lines are extracted and sub-patterns are automatically detected in the images. Then sub-patterns are matched based on a line representation in two ways: by their chain code representation and by their shape contexts. Promising results are obtained for finding the instances of a query pattern and for fully automatic detection of repeating patterns on a square kufic image collection.
Open Access
A new representation for matching words
(2007) Ataer, Esra
Large archives of historical documents are challenging to many researchers all over the world. However, these archives remain inaccessible since manual indexing and transcription of such a huge volume is difficult. In addition, electronic imaging tools and image processing techniques gain importance with the rapid increase in digitalization of materials in libraries and archives. In this thesis, a language independent method is proposed for representation of word images, which leads to retrieval and indexing of documents. While character recognition methods suffer from preprocessing and overtraining, we make use of another method, which is based on extracting words from documents and representing each word image with the features of invariant regions. The bag-of-words approach, which is shown to be successful to classify objects and scenes, is adapted for matching words. Since the curvature or connection points, or the dots are important visual features to distinct two words from each other, we make use of the salient points which are shown to be successful in representing such distinctive areas and heavily used for matching. Difference of Gaussian (DoG) detector, which is able to find scale invariant regions, and Harris Affine detector, which detects affine invariant regions, are used for detection of such areas and detected keypoints are described with Scale Invariant Feature Transform (SIFT) features. Then, each word image is represented by a set of visual terms which are obtained by vector quantization of SIFT descriptors and similar words are matched based on the similarity of these representations by using different distance measures. These representations are used both for document retrieval and word spotting. The experiments are carried out on Arabic, Latin and Ottoman datasets, which included different writing styles and different writers. The results show that the proposed method is successful on retrieval and indexing of documents even if with different scripts and different writers and since it is language independent, it can be easily adapted to other languages as well. Retrieval performance of the system is comparable to the state of the art methods in this field. In addition, the system is succesfull on capturing semantic similarities, which is useful for indexing, and it does not include any supervising step.
Open Access
Segmentation based Ottoman text and matching based Kufic image analysis
(2013) Adıgüzel, Hande
Large archives of historical documents attract many researchers from all around the world. The increasing demand to access those archives makes automatic retrieval and recognition of historical documents crucial. Ottoman archives are one of the largest collections of historical documents. Although Ottoman is not a currently spoken language, many researchers from all around the world are interested in accessing the archived material. This thesis proposes two Ottoman document analysis studies; first one is a crucial pre-processing task for retrieval and recognition which is segmentation of documents. Second one is a more specific retrieval and recognition problem which aims matching Islamic patterns is Kufic images. For the first segmentation task, layout, line and word segmentation is studied. Layout segmentation is obtained via Log-Gabor filtering. Four different algorithms are proposed for line segmentation and finally a simple morphological method is preferred for word segmentation. Datasets are constructed with documents from both Ottoman and other languages (English, Greek and Bangla) to test the script-independency of the methods. Experiments show that our segmentation steps give satisfactory results. The second task aims to detect Islamic patterns in Kufic images. The sub-patterns are considered as basic units and matching is used for the analysis. Graphs are preferred to represent subpatterns where graph and sub-graph isomorphism are used for matching them. Kufic images are analyzed in three different ways. Given a query pattern, all the instances of the query can be found through retrieval. Going further, through known patterns images can be automatically labeled in the entire dataset. Finally, patterns that repeat inside an image can be automatically discovered. As there is no existing Kufic dataset, a new one is constructed by collecting images from the Internet and promising results are obtained on this dataset.