ICDAR2019 Robust Reading Challenge on Arbitrary-Shaped Text - RRC-ArT

Chng, Chee Kheng; Ding, Errui; Liu, Jingtuo; Karatzas, Dìmosthenis; Chan, Chee Seng; Jin, Lianwen; Liu, Yuliang; Sun, Yuliang; Ng, Chun Chet; Luo, Canjie; Ni, Zihan; Fang, Chuanming; Zhang, Shuaitao; Han, Junyu

doi:10.1109/icdar.2019.00252

Cited by 129 publications

(49 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Note that 15k COCO-Text [87] images in our previous manuscript [16] are not used in this improved version. For ReCTS dataset, we adopt LSVT [88], ArT [89], ReCTS [39], and the synthetic pretrained data to train the model.…”

Section: Implementation Detailsmentioning

confidence: 99%

“…ICDAR'19-ArT dataset [89] is currently the largest dataset for arbitrarily shaped scene text. It is the combination and extension of the Total-text and SCUT-CTW1500.…”

Section: Benchmarksmentioning

confidence: 99%

“…It provides total 450k images with rich information of the real scene, among which 50k are annotated in full annotations (30k for training and the rest 20k for testing). Similar to ArT [89], this dataset also contains some curved text, which are annotated with polygon.…”

Section: Benchmarksmentioning

confidence: 99%

See 2 more Smart Citations

ABCNet v2: Adaptive Bezier-Curve Network for Real-time End-to-end Text Spotting

Liu¹,

Shen²,

Jin³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

End-to-end text-spotting, which aims to integrate detection and recognition in a unified framework, has attracted increasing attention due to its simplicity of the two complimentary tasks. It remains an open problem especially when processing arbitrarily-shaped text instances. Previous methods can be roughly categorized into two groups: character-based and segmentation-based, which often require character-level annotations and/or complex post-processing due to the unstructured output.Here, we tackle end-to-end text spotting by presenting Adaptive Bezier Curve Network v2 (ABCNet v2). Our main contributions are four-fold: 1) For the first time, we adaptively fit arbitrarily-shaped text by a parameterized Bezier curve, which, compared with segmentation-based methods, can not only provide structured output but also controllable representation. 2) We design a novel BezierAlign layer for extracting accurate convolution features of a text instance of arbitrary shapes, significantly improving the precision of recognition over previous methods. 3) Different from previous methods, which often suffer from complex post-processing and sensitive hyper-parameters, our ABCNet v2 maintains a simple pipeline with the only post-processing non-maximum suppression (NMS). 4) As the performance of text recognition closely depends on feature alignment, ABCNet v2 further adopts a simple yet effective coordinate convolution to encode the position of the convolutional filters, which leads to a considerable improvement with negligible computation overhead. Comprehensive experiments conducted on various bilingual (English and Chinese) benchmark datasets demonstrate that ABCNet v2 can achieve state-of-the-art performance while maintaining very high efficiency. More importantly, as there is little work on quantization of text spotting models, we quantize our models to improve the inference time of the proposed ABCNet v2. This can be valuable for real-time applications. Code and model are available at: https://git.io/AdelaiDet

show abstract

Section: Implementation Detailsmentioning

confidence: 99%

“…ICDAR'19-ArT dataset [89] is currently the largest dataset for arbitrarily shaped scene text. It is the combination and extension of the Total-text and SCUT-CTW1500.…”

Section: Benchmarksmentioning

confidence: 99%

See 1 more Smart Citation

ABCNet v2: Adaptive Bezier-Curve Network for Real-time End-to-end Text Spotting

Liu¹,

Shen²,

Jin³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…In the experiments, ICDAR2019 Art [ 31 ], LSVT [ 32 ], and ReCTs [ 33 ] generate the text dataset and its inverse that are used for training. Verification is performed on the training set of RCTW-17 [ 34 ], and the test set of RCTW-17 serves as the test set.…”

Section: Experiments On Detection and Recognition Modelsmentioning

confidence: 99%

A Robot Object Recognition Method Based on Scene Text Reading in Home Environments

Shu-hua

et al. 2021

Sensors

View full text Add to dashboard Cite

With the aim to solve issues of robot object recognition in complex scenes, this paper proposes an object recognition method based on scene text reading. The proposed method simulates human-like behavior and accurately identifies objects with texts through careful reading. First, deep learning models with high accuracy are adopted to detect and recognize text in multi-view. Second, datasets including 102,000 Chinese and English scene text images and their inverse are generated. The F-measure of text detection is improved by 0.4% and the recognition accuracy is improved by 1.26% because the model is trained by these two datasets. Finally, a robot object recognition method is proposed based on the scene text reading. The robot detects and recognizes texts in the image and then stores the recognition results in a text file. When the user gives the robot a fetching instruction, the robot searches for corresponding keywords from the text files and achieves the confidence of multiple objects in the scene image. Then, the object with the maximum confidence is selected as the target. The results show that the robot can accurately distinguish objects with arbitrary shape and category, and it can effectively solve the problem of object recognition in home environments.

show abstract

“…EAST [22] directly regresses rotated rectangles or quadrangles of text through a simplified pipeline without using any anchors. In recent years, curved text [23] has attracted the interest of the research community because rectangular or quadrilateral annotations loosely bound curved text. Mask textspotter [24] built a model based on the framework of Mask R-CNN [25] and performed character-level instance segmentation for each alphabet.…”

Section: A Scene Text Detectionmentioning

confidence: 99%

Stroke-Based Scene Text Erasing Using Synthetic Data for Training

Tang,

Miyazaki,

Sugaya

et al. 2021

Preprint

View full text Add to dashboard Cite

Scene text erasing, which replaces text regions with reasonable content in natural images, has drawn attention in the computer vision community in recent years. There are two potential subtasks in scene text erasing: text detection and image inpainting. Either sub-task requires considerable data to achieve better performance; however, the lack of a large-scale real-world scene-text removal dataset allows the existing methods to not work in full strength. To avoid the limitation of the lack of pairwise real-world data, we enhance and make full use of the synthetic text and consequently train our model only on the dataset generated by the improved synthetic text engine. Our proposed network contains a stroke mask prediction module and background inpainting module that can extract the text stroke as a relatively small hole from the text image patch to maintain more background content for better inpainting results. This model can partially erase text instances in a scene image with a bounding box provided or work with an existing scene text detector for automatic scene text erasing. The experimental results of qualitative evaluation and quantitative evaluation on the SCUT-Syn, ICDAR2013, and SCUT-EnsText datasets demonstrate that our method significantly outperforms existing state-of-the-art methods even when trained on real-world data.

show abstract

ICDAR2019 Robust Reading Challenge on Arbitrary-Shaped Text - RRC-ArT

Cited by 129 publications

References 11 publications

ABCNet v2: Adaptive Bezier-Curve Network for Real-time End-to-end Text Spotting

ABCNet v2: Adaptive Bezier-Curve Network for Real-time End-to-end Text Spotting

A Robot Object Recognition Method Based on Scene Text Reading in Home Environments

Stroke-Based Scene Text Erasing Using Synthetic Data for Training

Contact Info

Product

Resources

About