Detecting Curve Text in the Wild: New Dataset and New Solution

By Yuliang Liu, Lianwen Jin, Shuaitao Zhang, Sheng Zhang. arXiv.org, 2017

295 citations recorded by the source corpus.

Scene text detection has been made great progress in recent years. The detection manners are evolving from axis-aligned rectangle to rotated rectangle and further to quadrangle. However, current datasets contain very little curve text, which can be widely observed in scene images such as signboard, product name and so on. To raise the concerns of reading curve text in the wild, in this paper, we construct a curve text dataset named CTW1500, which includes over 10k text annotations in 1,500 images (1000 for training and 500 for testing). Based on this dataset, we pioneering propose a polygon based curve text detector (CTD) which can directly detect curve text without empirical combination. Moreover, by seamlessly integrating the recurrent transverse and longitudinal offset connection (TLOC), the proposed method can be end-to-end trainable to learn the inherent connection among the position offsets. This allows the CTD to explore context information instead of predicting points independently, resulting in more smooth and accurate detection. We also propose two simple but effective post-processing methods named non-polygon suppress (NPS) and polygonal non-maximum suppression (PNMS) to further improve the detection accuracy. Furthermore, the proposed approach in this paper is designed in an universal manner, which can also be trained with rectangular or quadrilateral bounding boxes without extra efforts. Experimental results on CTW-1500 demonstrate our method with only a light backbone can outperform state-of-the-art methods with a large margin. By evaluating only in the curve or non-curve subset, the CTD + TLOC can still achieve the best results. Code is available at this https URL

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/fcdf5055c902ec2d1570e598121f980a71fb90ca

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

Transformers in Remote Sensing: A Survey (2022, methodology): “RBox [42] Detection SynthText [89], ICDAR 2015 (IC15) [90], MLT-2017 (MLT17) [91], MSRA-TD500 [92], MTWI [93], Total-Text [94], CTW1500 [95] mAP Proposes a framework employing transformers to model the relationship of sampled features for better grouping and box prediction without requiring post-pro”
TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes (2018, background): “CTW1500 [43] is another dataset mainly consisting of curved text.”
Shape Robust Text Detection With Progressive Scale Expansion Network (2018, methodology): “* indicates the results from [24].”
Look More Than Once: An Accurate Detector for Text of Arbitrary Shapes (2019, methodology): “Benefits from SEM: We evaluate the benefits of SEM on SCUT-CTW1500 [39] in Tab.”
TextOCR: Towards large-scale end-to-end reasoning for arbitrary-shaped scene text (2021, methodology): “4 11 MSRA-TD500 [61] 300 200 – – – 12 CTW-1500 [34] 1000 500 – – – 13 COCO-Text [57] 18895 4416 61793 13910 3.”
Efficient and Accurate Arbitrary-Shaped Text Detection With Pixel Aggregation Network (2019, methodology): “Arbitrary-shaped text detection, one of the most challenging tasks in text detection, is receiving more and more research attention Some new methods [31, 35, 49, 24] have been put forward to detect curve text instance.”
Sliding Line Point Regression for Shape Robust Scene Text Detection (2018, methodology): “In recent years, other NMS approaches were investigated, e.g., locality-aware NMS [10], inclined NMS [11], Mask-NMS [9] and polygonal NMS (PNMS) [13].”
Character Region Awareness for Text Detection (2019, methodology): “CTW-1500 dataset [38] provides polygon-only annotations without text transcriptions.”