Convolutional Feature Fusion for Multi-Language Text Detection in Natural Scene Images
Asghar Ali Chandio, Mark R. Pickering · 2019 2nd International Conference on Computing, Mathematics and Engineering Technologies (iCoMET) · 2019
In this paper, we propose a feature fusion of convolutional layers in a VGG-16 network to detect multi-lingual text in natural scenes. A Fast-RCNN network is used to generate the text/non-text proposals, which are then passed to the recurrent neural network to connect them sequentially. The recurrent neural network is implemented within the convolutional network. The proposed network is trained on a combined ICDAR 2017 multi-lingual natural scene text dataset and a custom manually labeled Urdu text dataset. The text in the Urdu natural images usually has variations in font sizes, patterns, alignment and writing styles. Urdu text is formed by joining two or more characters and the words or sentences generally overlap with other text. Therefore, accurate detection of Arabic and Urdu text in natural scenes is complex, and challenging. The proposed method achieves favorable results for Arabic and Urdu text detection in natural scene images.