Text Flow: A Unified Text Detection System in Natural Scene Images

Tian, Shangxuan; Pan, Yifeng; Huang, Chang; Lu, Shijian; Yu, Kai; Tan, Chew Lim

doi:10.1109/iccv.2015.528

Cited by 193 publications

(117 citation statements)

References 25 publications

Supporting

Mentioning

116

Contrasting

Order By: Relevance

“…Therefore, the character seems to be a more natural choice to set up a general text detection engine. Previously, some character based methods [42,31,9,14] have achieved good performances on some public benchmarks that have characterlevel annotations (such as ICDAR13 [16]). However, as it is not convenient and economic to acquire character-level annotations, more and more public benchmarks (such as ICDAR15 [15] and MSRA-TD500 [35]) provide only word-level annotations.…”

Section: Related Workmentioning

confidence: 99%

Detecting Text in the Wild with Deep Character Embedding Network

Zhang

Sun

et al. 2019

Computer Vision – ACCV 2018

View full text Add to dashboard Cite

Most text detection methods hypothesize texts are horizontal or multi-oriented and thus define quadrangles as the basic detection unit. However, text in the wild is usually perspectively distorted or curved, which can not be easily tackled by existing approaches. In this paper, we propose a deep character embedding network (CENet) which simultaneously predicts the bounding boxes of characters and their embedding vectors, thus making text detection a simple clustering task in the character embedding space. The proposed method does not require strong assumptions of forming a straight line on general text detection, which provides flexibility on arbitrarily curved or perspectively distorted text. For character detection task, a dense prediction subnetwork is designed to obtain the confidence score and bounding boxes of characters. For character embedding task, a subnet is trained with contrastive loss to project detected characters into embedding space. The two tasks share a backbone CNN from which the multi-scale feature maps are extracted. The final text regions can be easily achieved by a thresholding process on character confidence and embedding distance of character pairs. We evaluated our method on ICDAR13, ICDAR15, MSRA-TD500, and Total Text. The proposed method achieves state-of-the-art or comparable performance on all of the datasets, and shows a substantial improvement in the irregular-text datasets, i.e. Total-Text.

show abstract

Section: Related Workmentioning

confidence: 99%

Detecting Text in the Wild with Deep Character Embedding Network

Zhang

Sun

et al. 2019

Computer Vision – ACCV 2018

View full text Add to dashboard Cite

show abstract

“…Scene text detection Different from general objects, scene texts are usually smaller, thinner, and with characteristic texture and rich diversity in their aspect ratios (Tian et al 2015).…”

Section: Related Workmentioning

confidence: 99%

DeRPN: Taking a Further Step toward More General Object Detection

Xie

Liu

Jin

et al. 2019

AAAI

View full text Add to dashboard Cite

Most current detection methods have adopted anchor boxes as regression references. However, the detection performance is sensitive to the setting of the anchor boxes. A proper setting of anchor boxes may vary significantly across different datasets, which severely limits the universality of the detectors. To improve the adaptivity of the detectors, in this paper, we present a novel dimension-decomposition region proposal network (DeRPN) that can perfectly displace the traditional Region Proposal Network (RPN). DeRPN utilizes an anchor string mechanism to independently match object widths and heights, which is conducive to treating variant object shapes. In addition, a novel scale-sensitive loss is designed to address the imbalanced loss computations of different scaled objects, which can avoid the small objects being overwhelmed by larger ones. Comprehensive experiments conducted on both general object detection datasets (Pascal VOC 2007, 2012 and MS COCO) and scene text detection datasets (ICDAR 2013 and COCO-Text) all prove that our DeRPN can significantly outperform RPN. It is worth mentioning that the proposed DeRPN can be employed directly on different models, tasks, and datasets without any modifications of hyperparameters or specialized optimization, which further demonstrates its adaptivity. The code will be released at https://github.com/HCIILAB/DeRPN.

show abstract

“…The word bounding boxes carry high level semantic information thus can be used to guide the semi-supervised process. A graph-based method [19] is used to group characters into words. This work performs well on horizontal text but could not be extended to multi-oriented or arbitrary shape situation.…”

Section: B Semi-and Weakly-supervised Scene Text Detectionmentioning

confidence: 99%

Curved Text Detection in Natural Scene Images with Semi- and Weakly-Supervised Learning

Qin

Zhou

Yang

et al. 2019

2019 International Conference on Document Analysis and Recognition (ICDAR)

View full text Add to dashboard Cite

Detecting curved text in the wild is very challenging. Recently, most state-of-the-art methods are segmentation based and require pixel-level annotations. We propose a novel scheme to train an accurate text detector using only a small amount of pixel-level annotated data and a large amount of data annotated with rectangles or even unlabeled data. A baseline model is first obtained by training with the pixellevel annotated data and then used to annotate unlabeled or weakly labeled data. A novel strategy which utilizes groundtruth bounding boxes to generate pseudo mask annotations is proposed in weakly-supervised learning. Experimental results on CTW1500 and Total-Text demonstrate that our method can substantially reduce the requirement of pixel-level annotated data. Our method can also generalize well across two datasets. The performance of the proposed method is comparable with the state-of-the-art methods with only 10% pixel-level annotated data and 90% rectangle-level weakly annotated data.

show abstract

Text Flow: A Unified Text Detection System in Natural Scene Images

Cited by 193 publications

References 25 publications

Detecting Text in the Wild with Deep Character Embedding Network

Detecting Text in the Wild with Deep Character Embedding Network

DeRPN: Taking a Further Step toward More General Object Detection

Curved Text Detection in Natural Scene Images with Semi- and Weakly-Supervised Learning

Contact Info

Product

Resources

About