|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
We propose a novel Connectionist Text Proposal Network (CTPN) that accurately localizes text lines in natural image.
The goal of COCO-Text is to advance state-of-the-art in text detection and recognition in natural images.
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.
#4 best model for Scene Text Detection on SCUT-CTW1500
To address these problems, we propose a novel Progressive Scale Expansion Network (PSENet), designed as a segmentation-based detector with multiple predictions for each text instance.
#5 best model for Scene Text Detection on SCUT-CTW1500
Yet, the widely adopted horizontal bounding box representation is not appropriate for ubiquitous oriented objects such as objects in aerial images and scene texts.
In this paper, we present an end-to-end trainable fast scene text detector, named TextBoxes++, which detects arbitrary-oriented scene text with both high accuracy and efficiency in a single network forward pass.
#2 best model for Scene Text Detection on COCO-Text
Most state-of-the-art scene text detection algorithms are deep learning based methods that depend on bounding box regression and perform at least two kinds of predictions: text/non-text classification and location regression.
#5 best model for Scene Text Detection on ICDAR 2013