Arabic text detection in videos using neural and boosting-based approaches: Application to video indexing

Sonia Yousfi (1) , Sid-Ahmed Berrani (2) , Christophe Garcia (1)

1 imagine - Extraction de Caractéristiques et Identification
2 Orange Labs - Orange Labs - Cesson-Sévigné

Text detection in videos is a primary step in any semanticbased video analysis systems. In this work, we propose and compare three machine learning-based methods for embedded Arabic text detection. These methods are able to detect Arabic text regions without any prior knowledge and without any pre-processing. The first method relies on a convolution neural network. The two other methods are based on a multiexit asymmetric boosting cascade. The proposed methods have been extensively evaluated on a large database of Arabic TV channel videos. Experiments highlight a good detection rate of all methods even though neural network-based method outperforms the other ones in terms of recall/precision and computation time.

Domaines: Informatique [cs]

Sonia Yousfi, Sid-Ahmed Berrani, Christophe Garcia. Arabic text detection in videos using neural and boosting-based approaches: Application to video indexing. International Conference on Image Processing (ICIP), Oct 2014, Paris, France. ⟨hal-01584915⟩