Deep Learning and Recurrent Connectionist-based Approaches for Arabic Text Recognition in Videos

Sonia Yousfi 1, 2 Sid-Ahmed Berrani 1 Christophe Garcia 2
2 imagine - Extraction de Caractéristiques et Identification
LIRIS - Laboratoire d'InfoRmatique en Image et Systèmes d'information
Abstract : This paper focuses on recognizing Arabic text embedded in videos. The proposed methods proceed without applying any prior pre-processing operations or character segmentation. Difficulties related to the video or text properties are faced using a learned robust representation of the input text image. This is performed using deep auto-encoders and Convolutional Neural Networks. Features are computed using a multiscale sliding window scheme. A connectionist recurrent approach is then used. It is trained to predict correct transcriptions of an input image from the associated sequence of features. Proposed methods are extensively evaluated on a large database of Arabic TV channels videos and compared to existing solutions.
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01152209
Contributor : Christophe Garcia <>
Submitted on : Friday, May 15, 2015 - 2:34:11 PM
Last modification on : Wednesday, November 20, 2019 - 2:59:21 AM

Identifiers

  • HAL Id : hal-01152209, version 1

Citation

Sonia Yousfi, Sid-Ahmed Berrani, Christophe Garcia. Deep Learning and Recurrent Connectionist-based Approaches for Arabic Text Recognition in Videos. 13th International Conference on Document Analysis and Recognition (ICDAR 2015), Aug 2015, Tunis, Tunisia. ⟨hal-01152209⟩

Share

Metrics

Record views

424