Deep Residual Text Detection Network for Scene Text
This work addresses scene text detection for computer vision applications, representing an incremental improvement over existing methods.
The paper tackled scene text detection by proposing a network using ResNet and multi-level features with a vertical proposal mechanism, achieving an F-measure of 0.91 on the ICDAR2013 dataset, outperforming previous state-of-the-art results.
Scene text detection is a challenging problem in computer vision. In this paper, we propose a novel text detection network based on prevalent object detection frameworks. In order to obtain stronger semantic feature, we adopt ResNet as feature extraction layers and exploit multi-level feature by combining hierarchical convolutional networks. A vertical proposal mechanism is utilized to avoid proposal classification, while regression layer remains working to improve localization accuracy. Our approach evaluated on ICDAR2013 dataset achieves F-measure of 0.91, which outperforms previous state-of-the-art results in scene text detection.