AON: Towards Arbitrarily-Oriented Text Recognition

Cheng, Zhanzhan; Xu, Yangliu; Bai, Fan; Niu, Yi; Pu, Shiliang; Zhou, Shuigeng

doi:10.48550/arxiv.1711.04226

Cited by 3 publications

(14 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As shown in Figure 4, our RCN is capable of calibrating the irregular text with various degrees of deformation, including the nearly vertical text. Compared with [5], we do not destroy the aspect ratio of text, and thus the characters have no deformation. We also re- port the recognition performance on Total-Text that has not been recorded in previous literature.…”

Section: Performance On Irregular Benchmarksmentioning

confidence: 99%

“…However, the detection errors will affect the performance of subsequent rectification and recognition. Cheng et al [5] proposed that the visual representation of irregular text can be described as the combination of features in four directions. This approach is able to effectively capture the deep features of irregular text, but the strategy of scaling word images to square will severely destroy the aspect ratio of text lines, especially for long text.…”

Section: Related Workmentioning

confidence: 99%

“…However, this method used an exhausting multi-task learning strategy and the inaccurate attention regions will cause recognition errors. Cheng et al [5] proposed the arbitrary orientation network (AON) to extract scene text features in four directions and adopted a weighting mechanism to combine the four feature sequences of different directions. In order to extract features with the same dimension in four directions, AON has to resize the text image into a square shape.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Recurrent Calibration Network for Irregular Text Recognition

Gao,

Chen,

Wang

et al. 2018

Preprint

View full text Add to dashboard Cite

Scene text recognition has received increased attention in the research community. Text in the wild often possesses irregular arrangements, typically including perspective text, curved text, oriented text. Most existing methods are hard to work well for irregular text, especially for severely distorted text. In this paper, we propose a novel Recurrent Calibration Network (RCN) for irregular scene text recognition. The RCN progressively calibrates the irregular text to boost the recognition performance. By decomposing the calibration process into multiple steps, the irregular text can be calibrated to normal one step by step. Besides, in order to avoid the accumulation of lost information caused by inaccurate transformation, we further design a fiducial-point refinement structure to keep the integrity of text during the recurrent process. Instead of the calibrated images, the coordinates of fiducial points are tracked and refined, which implicitly models the transformation information. Based on the refined fiducial points, we estimate the transformation parameters and sample from the original image at each step. In this way, the original character information is preserved until the final transformation. Such designs lead to optimal calibration results to boost the performance of succeeding recognition. Extensive experiments on challenging datasets demonstrate the superiority of our method, especially on irregular benchmarks.

show abstract

Section: Performance On Irregular Benchmarksmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Recurrent Calibration Network for Irregular Text Recognition

Gao,

Chen,

Wang

et al. 2018

Preprint

View full text Add to dashboard Cite

show abstract

“…Scene text recognition refers to recognizing a sequence of characters that appear in a natural image. Inspired by the success [1] in neural machine translation, many of the recently proposed scene text recognizers [2,3,4,5,6] adopt an encoder-decoder framework with an attention mechanism. Despite the remarkable results reported by them, very few of them have addressed the problem of having characters with different scales in the image.…”

Section: Introductionmentioning

confidence: 99%

“…1 shows some examples of text images containing characters with different scales. Existing text recognizers [2,3,4,5,6,7,8] employ only one single convolutional neural network for feature encoding, and often perform poorly for such text images. Note that a single-CNN encoder with a fixed receptive field 1 (refer to the green rectangles in Fig.…”

Section: Introductionmentioning

confidence: 99%

SAFE: Scale Aware Feature Encoder for Scene Text Recognition

Liu

Chen

Wong

2019

Computer Vision – ACCV 2018

View full text Add to dashboard Cite

In this paper, we address the problem of having characters with different scales in scene text recognition. We propose a novel scale aware feature encoder (SAFE) that is designed specifically for encoding characters with different scales. SAFE is composed of a multi-scale convolutional encoder and a scale attention network. The multi-scale convolutional encoder targets at extracting character features under multiple scales, and the scale attention network is responsible for selecting features from the most relevant scale(s). SAFE has two main advantages over the traditional single-CNN encoder used in current state-of-the-art text recognizers. First, it explicitly tackles the scale problem by extracting scale-invariant features from the characters. This allows the recognizer to put more effort in handling other challenges in scene text recognition, like those caused by view distortion and poor image quality. Second, it can transfer the learning of feature encoding across different character scales. This is particularly important when the training set has a very unbalanced distribution of character scales, as training with such a dataset will make the encoder biased towards extracting features from the predominant scale. To evaluate the effectiveness of SAFE, we design a simple text recognizer named scale-spatial attention network (S-SAN) that employs SAFE as its feature encoder, and carry out experiments on six public benchmarks. Experimental results demonstrate that S-SAN can achieve state-of-the-art (or, in some cases, extremely competitive) performance without any post-processing.

show abstract