Extraction and Recognition of Artificial Text in Multimedia Documents

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 processing. The quality of the localized text is improved by robust multiple frame integration. A new technique for the binarization of the text boxes based on a criterion maximizing local contrast is proposed. Finally, detection and OCR results for a commercial OCR are presented, justifying the choice of the binarization technique
Document type :
Journal articles
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01504401
Contributor : Équipe Gestionnaire Des Publications Si Liris <>
Submitted on : Monday, April 10, 2017 - 9:34:39 AM
Last modification on : Tuesday, February 26, 2019 - 1:46:01 PM
Long-term archiving on : Tuesday, July 11, 2017 - 12:21:45 PM

File

Liris-753.pdf
Files produced by the author(s)

Identifiers

Citation

Christian Wolf, Jean-Michel Jolion. Extraction and Recognition of Artificial Text in Multimedia Documents. Pattern Analysis and Applications, Springer Verlag, 2004, 4, 6, pp.309-326. ⟨10.1007/s10044-003-0197-7⟩. ⟨hal-01504401⟩

Share

Metrics

Record views

217

Files downloads

376