EK-Net:Real-time Scene Text Detection with Expand Kernel Distance
This addresses the problem of real-time and accurate text detection in complex scenes for applications like document analysis, but it is incremental as it builds on existing methods to fix a specific deficiency.
The paper tackles the challenge of accurate scene text detection in complex scenes with multiple scales, orientations, and curvature by proposing EK-Net, which achieves state-of-the-art or competitive performance, such as an F-measure of 85.72% at 35.42 FPS on ICDAR 2015.
Recently, scene text detection has received significant attention due to its wide application. However, accurate detection in complex scenes of multiple scales, orientations, and curvature remains a challenge. Numerous detection methods adopt the Vatti clipping (VC) algorithm for multiple-instance training to address the issue of arbitrary-shaped text. Yet we identify several bias results from these approaches called the "shrinked kernel". Specifically, it refers to a decrease in accuracy resulting from an output that overly favors the text kernel. In this paper, we propose a new approach named Expand Kernel Network (EK-Net) with expand kernel distance to compensate for the previous deficiency, which includes three-stages regression to complete instance detection. Moreover, EK-Net not only realize the precise positioning of arbitrary-shaped text, but also achieve a trade-off between performance and speed. Evaluation results demonstrate that EK-Net achieves state-of-the-art or competitive performance compared to other advanced methods, e.g., F-measure of 85.72% at 35.42 FPS on ICDAR 2015, F-measure of 85.75% at 40.13 FPS on CTW1500.