56 papers with code • 9 benchmarks • 11 datasets
Scene Text Detection is a task to detect text regions in the complex background and label them with bounding boxes.
With a PG-CTC decoder, we gather high-level character classification vectors from two-dimensional space and decode them into text symbols without NMS and RoI operations involved, which guarantees high efficiency.
Ranked #1 on Scene Text Detection on ICDAR 2015 (Accuracy metric)
Recently, segmentation-based methods are quite popular in scene text detection, as the segmentation results can more accurately describe scene text of various shapes such as curve text.
Ranked #2 on Scene Text Detection on MSRA-TD500
We propose a novel Connectionist Text Proposal Network (CTPN) that accurately localizes text lines in natural image.
Recently, some methods have been proposed to tackle arbitrary-shaped text detection, but they rarely take the speed of the entire pipeline into consideration, which may fall short in practical applications. In this paper, we propose an efficient and accurate arbitrary-shaped text detector, termed Pixel Aggregation Network (PAN), which is equipped with a low computational-cost segmentation head and a learnable post-processing.
Ranked #1 on Scene Text Detection on MSRA-TD500
Due to the fact that there are large geometrical margins among the minimal scale kernels, our method is effective to split the close text instances, making it easier to use segmentation-based methods to detect arbitrary-shaped text instances.
Ranked #5 on Scene Text Detection on SCUT-CTW1500