Deep TextSpotter: An End-to-End Trainable Scene Text Localization and Recognition Framework

Bušta, Michal; Neumann, Lukáš; Matas, Jiřı́

doi:10.1109/iccv.2017.242

Cited by 238 publications

(199 citation statements)

References 11 publications

Supporting

Mentioning

193

Contrasting

Unclassified

Order By: Relevance

“…Those approaches can be divided into two major groups: two-stage proposal-driven and onestage proposal-free method. Although two-stage framework [37,24,10] consistently achieves top accuracy on the public benchmarks [12,11,25], recent works [16,22,2,9] based on one-stage frameworks also demonstrate yielding faster text detectors with comparable accuracy.…”

Section: Introductionmentioning

confidence: 94%

“…In order to achieve multi-oriented text detection, DMPNet [22] added several rotated anchors, for a total of 12 (6 regular and 6 inclined) to find the best match to arbitrary-oriented text instance. Instead of choosing priors by hand, DeepTextSpotter [2] followed YOLOv2 [28] runs k-means clustering (k = 14) on the training set bounding boxes to automatically find suitable priors.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

STELA: A Real-Time Scene Text Detector With Learned Anchor

Deng

Gong

et al. 2019

IEEE Access

View full text Add to dashboard Cite

To achieve high coverage of target boxes, a normal strategy of conventional one-stage anchor-based detectors is to utilize multiple priors at each spatial position, especially in scene text detection tasks. In this work, we present a simple and intuitive method for multi-oriented text detection where each location of feature maps only associates with one reference box. The idea is inspired from the twostage R-CNN framework that can estimate the location of objects with any shape by using learned proposals. The aim of our method is to integrate this mechanism into a onestage detector and employ the learned anchor which is obtained through a regression operation to replace the original one into the final predictions. Based on RetinaNet, our method achieves competitive performances on several public benchmarks with a totally real-time efficiency (26.5f ps at 800p), which surpasses all of anchor-based scene text detectors. In addition, with less attention on anchor design, we believe our method is easy to be applied on other analogous detection tasks. The code will publicly available at https://github.com/xhzdeng/stela.

show abstract

Section: Introductionmentioning

confidence: 94%

Section: Introductionmentioning

confidence: 99%

STELA: A Real-Time Scene Text Detector With Learned Anchor

Deng

Gong

et al. 2019

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Perspective RoI Transform: Given quadrangle text proposals predicted by the detection branch, we employ the perspective RoI transform [37] to align the corresponding regions from the feature map F into small feature maps F p rather than wrapping proposals in rotated rectangles [8][28] [14]. Each feature map F p is kept in a fixed height with an unchanged aspect ratio.…”

Section: End-to-end Chinese Text Readingmentioning

confidence: 99%

Chinese Street View Text: Large-Scale Chinese Text Reading With Partially Supervised Learning

Sun

Liu

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

Most existing text reading benchmarks make it difficult to evaluate the performance of more advanced deep learning models in large vocabularies due to the limited amount of training data. To address this issue, we introduce a new large-scale text reading benchmark dataset named Chinese Street View Text (C-SVT) with 430, 000 street view images, which is at least 14 times as large as the existing Chinese text reading benchmarks. To recognize Chinese text in the wild while keeping large-scale datasets labeling cost-effective, we propose to annotate one part of the C-SVT dataset (30,000 images) in locations and text labels as full annotations and add 400, 000 more images, where only the corresponding text-of-interest in the regions is given as weak annotations. To exploit the rich information from the weakly annotated data, we design a text reading network in a partially supervised learning framework, which enables to localize and recognize text, learn from fully and weakly annotated data simultaneously. To localize the best matched text proposals from weakly labeled images, we propose an online proposal matching module incorporated in the whole model, spotting the keyword regions by sharing parameters for end-to-end training. Compared with fully supervised training algorithms, this model can improve the end-to-end recognition performance remarkably by 4.03% in F-score at the same labeling cost. The proposed model can also achieve state-of-the-art results on the ICDAR 2017-RCTW dataset, which demonstrates the effectiveness of the proposed partially supervised learning framework.

show abstract

“…Liao et al [14], [15] use a single-shot text detector along with a text recognizer to detect and recognize horizontal and oriented scene text in images respectively. [16], [17] start to integrate the scene text detection and recognition modules into a unified framework. [5] propose an end-to-end trainable scene text spotter enjoying a simple pipeline and can handle text of various shapes.…”

Section: B Differences From Scene Text Spottingmentioning

confidence: 99%

A Multi-oriented Chinese Keyword Spotter Guided by Text Line Detection

Huang

Wang

et al. 2019

2019 International Conference on Document Analysis and Recognition (ICDAR)

View full text Add to dashboard Cite

Chinese keyword spotting is a challenging task as there is no visual blank for Chinese words. Different from English words which are split naturally by visual blanks, Chinese words are generally split only by semantic information. In this paper, we propose a new Chinese keyword spotter for natural images, which is inspired by Mask R-CNN. We propose to predict the keyword masks guided by text line detection. Firstly, proposals of text lines are generated by Faster R-CNN;Then, text line masks and keyword masks are predicted by segmentation in the proposals. In this way, the text lines and keywords are predicted in parallel. We create two Chinese keyword datasets based on RCTW-17 and ICPR MTWI2018 to verify the effectiveness of our method.

show abstract

Deep TextSpotter: An End-to-End Trainable Scene Text Localization and Recognition Framework

Cited by 238 publications

References 11 publications

STELA: A Real-Time Scene Text Detector With Learned Anchor

STELA: A Real-Time Scene Text Detector With Learned Anchor

Chinese Street View Text: Large-Scale Chinese Text Reading With Partially Supervised Learning

A Multi-oriented Chinese Keyword Spotter Guided by Text Line Detection

Contact Info

Product

Resources

About