Symmetry-Constrained Rectification Network for Scene Text Recognition

Yang, Mingkun; Guan, Yushuo; Liao, Minghui; He, Xin; Bian, Kaigui; Bai, Song; Yao, Cong; Bai, Xiang

doi:10.1109/iccv.2019.00924

Cited by 159 publications

(126 citation statements)

References 46 publications

Supporting

Mentioning

119

Contrasting

Order By: Relevance

“…We observe that our method outperforms [20] by 4.9% on CUTE80 and 1.6% on SVTP. Although our network is supervised with only word-level annotations, it still performs better than the methods trained with both word-level and character-level annotations [4,7,17,40] on nearly all the benchmarks. We also find that the performance gains on the curved text benchmarks are better than those on the perspective text benchmarks.…”

Section: Performance On Irregular Benchmarksmentioning

confidence: 91%

“…Zhan and Lu [20] designed a fix-order polynomial to represent irregular text orientation. Yang et al [7] added symmetrical constraints in the rectification module, which relied on character-level annotations.…”

Section: Related Workmentioning

confidence: 99%

“…however, applying these approaches to identify distorted text is difficult. One idea is to rectify irregular text into an easy-to-recognize front-horizontal view [5][6][7]. The spatial transformer network (ST-Net) [8] is a learnable module that explicitly allows spatial manipulations.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Progressive rectification network for irregular text recognition

Gao

Chen

Wang

et al. 2020

Sci. China Inf. Sci.

View full text Add to dashboard Cite

Scene text recognition has received increasing attention in the research community. Text in the wild often possesses irregular arrangements, which typically include perspective, curved, and oriented texts. Most of the existing methods do not work well for irregular text, especially for severely distorted text. In this paper, we propose a novel progressive rectification network (PRN) for irregular scene text recognition. Our PRN progressively rectifies the irregular text to a front-horizontal view and further boosts the recognition performance. The distortions are removed step by step by leveraging the observation that the intermediate rectified result provides good guidance for subsequent higher quality rectification. Additionally, by decomposing the rectification process into multiple procedures, the difficulty of each step is considerably mitigated. First, we specifically perform a rough rectification, and then adopt iterative refinement to gradually achieve optimal rectification. Additionally, to avoid the boundary damage problem in direct iterations, we design an envelope-refinement structure to maintain the integrity of the text during the iterative process. Instead of the rectified images, the text line envelope is tracked and continually refined, which implicitly models the transformation information. Then, the original input image is consistently utilized for transformation based on the refined envelope. In this manner, the original character information is preserved until the final transformation. These designs lead to optimal rectification to boost the performance of succeeding recognition. Extensive experiments on eight challenging datasets demonstrate the superiority of our method, especially on irregular benchmarks.

show abstract

Section: Performance On Irregular Benchmarksmentioning

confidence: 91%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Progressive rectification network for irregular text recognition

Gao

Chen

Wang

et al. 2020

Sci. China Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…A more generic approach is proposed in [1] where an endto-end trainable CNN is used to locate the document and correct its distortion simultaneously. The used CNN can be trained to find the corners or also to directly predict the transformation matrix like in [24] and [26]. While [26] uses a CNN regression model and a hierarchy of Spatial Transformer Networks to directly estimate the homography between an image pair, [24] addresses irregular scene text rectification by directly rectifying the feature maps without any explicit homography estimation.…”

Section: A Document Localization Approachesmentioning

confidence: 99%

ID documents matching and localization with multi-hypothesis constraints

Chiron

Ghanmi

Awal

2021

2020 25th International Conference on Pattern Recognition (ICPR)

View full text Add to dashboard Cite

This paper presents an approach for spotting and accurately localizing identity documents in the wild. Contrary to blind solutions that often rely on borders and corners detection, the proposed approach requires a classification a priori along with a list of predefined models. The matching and accurate localization are performed using specific ID document features. This process is especially difficult due to the intrinsic variable nature of ID models (text fields, multi-pass printing with offset, unstable layouts, added artifacts, blinking security elements, nonrigid materials). We tackle the problem by putting different combinations of features in competition within a multi-hypothesis exploration where only the best document quadrilateral candidate is retained thanks to a custom visual similarity metric. The idea is to find, in a given context, at least one feature able to correctly crop the document. The proposed solution has been tested and has shown its benefits on both the MIDV-500 academic dataset and an industrial one supposedly more representative of a real-life application.Best selected hypothesis repatriation in docs % (-are ablated hypothesis)Accepted crops >0.9 Jaccard dist Keypoints 3D trans.

show abstract

“…In [60], text recognition is performed by extracting discriminative features and increasing the alignment between the target character region and attention region. The authors in [61] utilize text shape descriptors, such as center line, scale, and orientation to deal with highly curved or distorted text. NRTR [62] dispenses with recurrences and convolutions with a stacked self-attention module, where an encoder extracts features and a decoder perform the recognization of texts based on the output of the encoder.…”

Section: B Scene Text Recognitionmentioning

confidence: 99%

Cluttered TextSpotter: An End-to-End Trainable Light-Weight Scene Text Spotter for Cluttered Environment

2020

View full text Add to dashboard Cite

Scene text spotting aims at simultaneously localizing and recognizing text instances, symbols, and logos in natural scene images. Scene text detection and recognition approaches have received immense attention in computer vision research community. The presence of partial occlusion or truncation artifact due to the cluttered background of scene images creates an obstacle in perceiving the text instances, which makes the process of spotting very complex. In this paper, we propose a lightweight scene text spotter that can address the issue of cluttered environment of scene images. It is an end-to-end trainable deep neural network that uses local part information, global structural features, and context cue information of oriented region proposals for spotting text instances. It helps to localize in scene images with background clutters, where partially occluded text parts, truncation artifacts, and perspective distortions are present. We mitigate the problem of misclassification caused by inter-class interference by exploring inter-class separability and intra-class compactness. We also incorporate multi-language character segmentation and word-level recognition in a lightweight recognition module. We have used six publicly available benchmark datasets in different smart devices to illustrate the efficacy of the network.

show abstract

Symmetry-Constrained Rectification Network for Scene Text Recognition

Cited by 159 publications

References 46 publications

Progressive rectification network for irregular text recognition

Progressive rectification network for irregular text recognition

ID documents matching and localization with multi-hypothesis constraints

Cluttered TextSpotter: An End-to-End Trainable Light-Weight Scene Text Spotter for Cluttered Environment

Contact Info

Product

Resources

About