DGST : Discriminator Guided Scene Text detector
This addresses scene text detection for computer vision applications, representing an incremental improvement over existing segmentation-based methods.
The paper tackles scene text detection by proposing DGST, a conditional GAN-based framework that generates multi-scale soft text score maps to better represent text positions and reduce pixel adhesion. It achieves an F-measure of 87% on the ICDAR 2015 dataset, outperforming state-of-the-art methods.
Scene text detection task has attracted considerable attention in computer vision because of its wide application. In recent years, many researchers have introduced methods of semantic segmentation into the task of scene text detection, and achieved promising results. This paper proposes a detector framework based on the conditional generative adversarial networks to improve the segmentation effect of scene text detection, called DGST (Discriminator Guided Scene Text detector). Instead of binary text score maps generated by some existing semantic segmentation based methods, we generate a multi-scale soft text score map with more information to represent the text position more reasonably, and solve the problem of text pixel adhesion in the process of text extraction. Experiments on standard datasets demonstrate that the proposed DGST brings noticeable gain and outperforms state-of-the-art methods. Specifically, it achieves an F-measure of 87% on ICDAR 2015 dataset.