INVESTIGADORES
NEGRI Pablo Augusto
congresos y reuniones científicas
Título:
A cascade detector for text detection in natural scene images
Autor/es:
SHEHZAD MUHAMMAD HANIF; LIONEL PREVOST; PABLO NEGRI
Lugar:
Tampa, Florida, USA
Reunión:
Conferencia; International Conference on Pattern Recognition; 2008
Institución organizadora:
IAPR
Resumen:
In this paper, we present a text detection and localization method. Our detection technique is based on a cascade of boosted ensemble and localizer uses standard image processing techniques. We propose a small set of features (39 in total) capable of detecting varioustype of text in grey level natural scene images. Two weak learners, linear discriminant function and log likelihood-ratio test under gaussian assumption, are evaluated. Single features and combination of features are used to form weak classifiers. The proposed scheme is evaluated on 250 images taken from ICDAR 2003 robust reading and text locating database. The text detection rate is 86% and false alarms rate is 3x10−3 and the detector can process an image of 640x480 pixels in lessthan 2 seconds.
