This is the authors' abstract. We don't add key points for this paper.
At present, the complexity of the real scene, it has brought many challenges to the scene text detection. there are many problems including the diversity of the layout shape and size of the Chinese line of the natural scene image and the arbitrariness of the direction et al. Using the existing text detector, there may still be a large number of false detections; Therefore, in order to solve the above problems, we propose a dual branch attention detection network for the text detection in natural scenes based on the idea of regional regression, which simplifies the original operation steps and only needs to deal with the data containing threshold differentiation and the non-maximum suppression analysis of predicted geometry; The algorithm proposed in this paper has reached 78.88% F-measure on icdar2015 dataset and 89.02% F-measure on icdar2013 dataset
Answers are grounded in this paper and cite their sources.
No takes yet. Share an insight, caveat, or question.
Jiang et al. (2022) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: