Fused Text Segmentation Networks for Multi-oriented Scene Text Detection

Dai, Yuchen; Huang, Zheng; Gao, Yuting; Xu, Youxuan; Chen, Kai; Guo, Jie; Qiu, Weidong

doi:10.48550/arxiv.1709.03272

Cited by 18 publications

(23 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To the best of our knowledge, this is the best reported result in literature. Similar to [He et al, 2016a], we utilized an ensemble of 5 networks, while the backbones are ResNet101 (2 networks), ResNet50 (2 networks) and VGG (1 network). We used an ensemble of these 5 networks for proposing regions.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

IncepText: A New Inception-Text Module with Deformable PSROI Pooling for Multi-Oriented Scene Text Detection

Yang

Cheng

Zhou

et al. 2018

Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence

View full text Add to dashboard Cite

Incidental scene text detection, especially for multioriented text regions, is one of the most challenging tasks in many computer vision applications. Different from the common object detection task, scene text often suffers from a large variance of aspect ratio, scale, and orientation. To solve this problem, we propose a novel end-to-end scene text detector IncepText from an instance-aware segmentation perspective. We design a novel Inception-Text module and introduce deformable PSROI pooling to deal with multi-oriented text detection. Extensive experiments on ICDAR2015, RCTW-17, and MSRA-TD500 datasets demonstrate our method's superiority in terms of both effectiveness and efficiency. Our proposed method achieves 1st place result on ICDAR2015 challenge and the state-ofthe-art performance on other datasets. Moreover, we have released our implementation as an OCR product which is available for public access. 1

show abstract

Section: Resultsmentioning

confidence: 99%

“…In Figure 1, the basic feature extraction module is ResNet-50 [He et al, 2016a]. For scene text detection, finer feature information is very important especially for segmentation task, the final downsampling in res stage 5 may lose some useful information.…”

Section: Overviewmentioning

confidence: 99%

IncepText: A New Inception-Text Module with Deformable PSROI Pooling for Multi-Oriented Scene Text Detection

Yang

Cheng

Zhou

et al. 2018

Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence

View full text Add to dashboard Cite

show abstract

“…Usually, for improving the robustness of the model when encountering various orientations of texts, existing methods [20,25,26] make use of data augmentation that rotates source images to different angles to harvest sufficient data for training. Despite the effectiveness of data augmentation, the main drawback lies in learning all the possible transformations of augmented data require more network parameters, and it also may result in significant increase of training cost and over-fitting risk [27].…”

Section: Dual-roi Poolingmentioning

confidence: 99%

Detecting multi-oriented text with corner-based region proposals

et al. 2019

View full text Add to dashboard Cite

Previous approaches for scene text detection usually rely on manually defined sliding windows. This work presents an intuitive two-stage region-based method to detect multi-oriented text without any prior knowledge regarding the textual shape. In the first stage, we estimate the possible locations of text instances by detecting and linking corners instead of shifting a set of default anchors. The quadrilateral proposals are geometry adaptive, which allows our method to cope with various text aspect ratios and orientations. In the second stage, we design a new pooling layer named Dual-RoI Pooling which embeds data augmentation inside the region-wise subnetwork for more robust classification and regression over these proposals. Experimental results on public benchmarks confirm that the proposed method is capable of achieving comparable performance with state-of-the-art methods. The code is publicly available at https://github.com/xhzdeng/crpn.

show abstract

“…There are also many methods adopt box proposal based instance segmentation network such as Mask R-CNN [12] for text detection. [4] fuses multiple-layer feature map for RPN and RoI, finally predicts a segmentation map of text. [42] completes both of detection and recognition tasks on mask-branch by predicting word segmentation map and character instance segmentation map, a weighted edit distance measure is proposed to find the best-matched recognition result.…”

Section: Related Workmentioning

confidence: 99%

TextMountain: Accurate Scene Text Detection via Instance Segmentation

Zhu¹,

Du²

2018

Preprint

View full text Add to dashboard Cite

In this paper, we propose a novel scene text detection method named TextMountain. The key idea of TextMountain is making full use of border-center information. Different from previous works that treat center-border as a binary classification problem, we predict text center-border probability (TCBP) and text center-direction (TCD). The TCBP is just like a mountain whose top is text center and foot is text border. The mountaintop can separate text instances which cannot be easily achieved using semantic segmentation map and its rising direction can plan a road to top for each pixel on mountain foot at the group stage. The TCD helps TCBP learning better. Our label rules will not lead to the ambiguous problem with the transformation of angle, so the proposed method is robust to multi-oriented text and can also handle well with curved text. In inference stage, each pixel at the mountain foot needs to search the path to the mountaintop and this process can be efficiently completed in parallel, yielding the efficiency of our method compared with others. The experiments on MLT, ICDAR2015, RCTW-17 and SCUT-CTW1500 databases demonstrate that the proposed method achieves better or comparable performance in terms of both accuracy and efficiency. It is worth mentioning our method achieves an F-measure of 76.85% on MLT which outperforms the previous methods by a large margin. Code will be made available.

show abstract

Fused Text Segmentation Networks for Multi-oriented Scene Text Detection

Cited by 18 publications

References 31 publications

IncepText: A New Inception-Text Module with Deformable PSROI Pooling for Multi-Oriented Scene Text Detection

IncepText: A New Inception-Text Module with Deformable PSROI Pooling for Multi-Oriented Scene Text Detection

Detecting multi-oriented text with corner-based region proposals

TextMountain: Accurate Scene Text Detection via Instance Segmentation

Contact Info

Product

Resources

About