Text Detection and Recognition for Person Identification in Video - Archive ouverte HAL Access content directly
Conference Papers Year : 2011

Text Detection and Recognition for Person Identification in Video

Abstract

This article presents a demo of person search in audiovisual broadcast using only the text available in a video and in resources external to the video. We also present the different steps used to recognize characters in video for multi-modal person recognition systems. Text detection is realized using the text features (texture, color, contrast, geometry, temporal information). The text recognition itself is performed by the Google Tesseract free software. The method was successfully evaluated on a broadcast news corpus that contains 59 videos from the France 2 French TV channel.
Fichier principal
Vignette du fichier
Poignant-Thollard-Quenot-Besacier_CBMI2011.pdf (146.23 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-00763540 , version 1 (11-12-2012)

Identifiers

Cite

Johann Poignant, Franck Thollard, Georges Quénot, Laurent Besacier. Text Detection and Recognition for Person Identification in Video. CBMI 2011 - Internationnal Workshop on Content-Based Multimedia Indexing, Jun 2011, Madrid, Spain. pp.245-248, ⟨10.1109/CBMI.2011.5972553⟩. ⟨hal-00763540⟩
177 View
205 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More