1 - 3 of 3
Number of results to display per page
Search Results
2. A Human-Annotated Dataset of Scanned Images and OCR Texts from Medieval Documents: Supplementary Materials
- Creator:
- Novotný, Vít and Horák, Aleš
- Publisher:
- Masaryk University, Brno
- Type:
- text and corpus
- Subject:
- ocr, optical character recognition, language identification, image super-resolution, sr, and Medieval
- Language:
- Czech, English, German, and Latin
- Description:
- These are supplementary materials for an open dataset of scanned images and OCR texts from 19th and 20th century letterpress reprints of documents from the Hussite era. The dataset contains human annotations for layout analysis, OCR evaluation, and language identification and is available at http://hdl.handle.net/11234/1-4615. These supplementary materials contain OCR texts from different OCR engines for book pages for which we have both high-resolution scanned images and annotations for OCR evaluation.
- Rights:
- Public Domain Dedication (CC Zero), http://creativecommons.org/publicdomain/zero/1.0/, and PUB
3. Application of a New Set of Pseudo-Distances in Documents Categorization
- Creator:
- Gadri, S. and Moussaoui, A.
- Format:
- bez média and svazek
- Type:
- model:article and TEXT
- Subject:
- N -grams, language identification, text categorization, text mining, machine learning, Kullback-Leibler distance, X2 distance, and Cavnar-Trenkle distance
- Language:
- English
- Description:
- Automatic text classification is a very important task that consists in assigning labels (categories, groups, classes) to a given text based on a set of previously labeled texts called training set. The work presented in this paper treats the problem of automatic topical text categorization. It is a supervised classification because it works on a predefined set of classes and topical because it uses topics or subjects of texts as classes. In this context, we used a new approach based on $k$-NN algorithm, as well as a new set of pseudo-distances (distance metrics) known in the field of language identification. We also proposed a simple and effective method to improve the quality of performed categorization.
- Rights:
- http://creativecommons.org/publicdomain/mark/1.0/ and policy:public