Proceedings ArticleDOI
Text localization, enhancement and binarization in multimedia documents
Christian Wolf,J.-M. Jolion,Francoise Chassaing +2 more
- Vol. 2, pp 1037-1040
TLDR
An algorithm to localize artificial text in images and videos using a measure of accumulated gradients and morphological post processing to detect the text is presented and the quality of the localized text is improved by robust multiple frame integration.Abstract:
The systems currently available for content based image and video retrieval work without semantic knowledge, i.e. they use image processing methods to extract low level features of the data. The similarity obtained by these approaches does not always correspond to the similarity a human user would expect. A way to include more semantic knowledge into the indexing process is to use the text included in the images and video sequences. It is rich in information but easy to use, e.g. by key word based queries. In this paper we present an algorithm to localize artificial text in images and videos using a measure of accumulated gradients and morphological post processing to detect the text. The quality of the localized text is improved by robust multiple frame integration. Anew technique for the binarization of the text boxes is proposed. Finally, detection and OCR results for a commercial OCR are presented.read more
Citations
More filters
Dissertation
Apprentissage neuronal de caractéristiques spatio-temporelles pour la classification automatique de séquences vidéo
TL;DR: Cette these s'interesse a la problematique de the classification automatique des sequences video est de se demarquer de la methodologie dominante qui se base sur l'utilisation de caracteristiques concues manuellement, and de proposer des modeles qui soient les plus generiques possibles and independants du domaine.
Posted Content
Full-Page Text Recognition: Learning Where to Start and When to Stop
TL;DR: A new approach for full page text recognition based on regressions with Fully Convolutional Neural Networks and Multidimensional Long Short-Term Memory as contextual layers and only the position of the left side of the text lines are predicted.
Dissertation
Camera-Captured Document Image Analysis
TL;DR: This thesis designs a robust feature named connected component descriptor that is tailored for mosaicing camera-captured document images and addresses two critical issues often encountered in correspondence matching, the stability of features and robustness against false matches due to multiple instances of many characters in a document image.
Journal ArticleDOI
A Novel Degraded Document Binarization Model through Vision Transformer Network
Mingming Yang,Songhua Xu +1 more
TL;DR: Wang et al. as mentioned in this paper proposed a dual-branched encoding feature fusion module, which combines architectural components from the vision transformer framework and deep convolutional neural networks to extract features from an input document that are sensitive to both global and local characteristics.
Journal ArticleDOI
Restoration of deteriorated text sections in ancient document images using a tri-level semi-adaptive thresholding technique
TL;DR: The proposed research aims to restore deteriorated text sections that are affected by stain markings, ink seepages and document ageing in ancient document photographs, as these challenges confront document enhancement with a tri-level semi-adaptive thresholding technique.
References
More filters
IEEE transactions on pattern analysis and machine intelligence
TL;DR: This special issue aims at gathering the recent advances in learning with shared information methods and their applications in computer vision and multimedia analysis and addressing interesting real-world computer Vision and multimedia applications.
Journal ArticleDOI
Goal-directed evaluation of binarization methods
O.D. Trier,Anil K. Jain +1 more
TL;DR: This paper presents a methodology for evaluation of low-level image analysis methods, using binarization (two-level thresholding) as an example, and defines the performance of the character recognition module as the objective measure.
Proceedings ArticleDOI
Automatic text location in images and video frames
Anil K. Jain,Bin Yu +1 more
TL;DR: Compared with some traditional text location methods, this method has the following advantages: 1) low computational cost; 2) robust to font size; and 3) high accuracy.