Scene Text Recognition via Transformer

• URL: http://arxiv.org/abs/2003.08077v4
• Date: Wed, 29 Apr 2020 02:56:28 GMT
• Title: Scene Text Recognition via Transformer
• Authors: Xinjie Feng, Hongxun Yao, Yuankai Qi, Jun Zhang, and Shengping Zhang
• Abstract summary: Scene text recognition with arbitrary shape is very challenging due to large variations in text shapes, fonts, colors, backgrounds, etc. Most state-of-the-art algorithms rectify the input image into the normalized image, then treat the recognition as a sequence prediction task. We propose a simple but extremely effective scene text recognition method based on transformer [50].
• Score: 36.55457990615167
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Scene text recognition with arbitrary shape is very challenging due to large variations in text shapes, fonts, colors, backgrounds, etc. Most state-of-the-art algorithms rectify the input image into the normalized image, then treat the recognition as a sequence prediction task. The bottleneck of such methods is the rectification, which will cause errors due to distortion perspective. In this paper, we find that the rectification is completely unnecessary. What all we need is the spatial attention. We therefore propose a simple but extremely effective scene text recognition method based on transformer [50]. Different from previous transformer based models [56,34], which just use the decoder of the transformer to decode the convolutional attention, the proposed method use a convolutional feature maps as word embedding input into transformer. In such a way, our method is able to make full use of the powerful attention mechanism of the transformer. Extensive experimental results show that the proposed method significantly outperforms state-of-the-art methods by a very large margin on both regular and irregular text datasets. On one of the most challenging CUTE dataset whose state-of-the-art prediction accuracy is 89.6%, our method achieves 99.3%, which is a pretty surprising result. We will release our source code and believe that our method will be a new benchmark of scene text recognition with arbitrary shapes.

Related papers

• Transformer based Pluralistic Image Completion with Reduced Information Loss [72.92754600354199]
  Transformer based methods have achieved great success in image inpainting recently. They regard each pixel as a token, thus suffering from an information loss issue. We propose a new transformer based framework called "PUT"
  arXiv  Detail & Related papers  (2024-03-31T01:20:16Z)
• Efficiently Leveraging Linguistic Priors for Scene Text Spotting [63.22351047545888]
  This paper proposes a method that leverages linguistic knowledge from a large text corpus to replace the traditional one-hot encoding used in auto-regressive scene text spotting and recognition models. We generate text distributions that align well with scene text datasets, removing the need for in-domain fine-tuning. Experimental results show that our method not only improves recognition accuracy but also enables more accurate localization of words.
  arXiv  Detail & Related papers  (2024-02-27T01:57:09Z)
• LRANet: Towards Accurate and Efficient Scene Text Detection with Low-Rank Approximation Network [63.554061288184165]
  We propose a novel parameterized text shape method based on low-rank approximation. By exploring the shape correlation among different text contours, our method achieves consistency, compactness, simplicity, and robustness in shape representation. We implement an accurate and efficient arbitrary-shaped text detector named LRANet.
  arXiv  Detail & Related papers  (2023-06-27T02:03:46Z)
• Portmanteauing Features for Scene Text Recognition [15.961450585164144]
  State-of-the-art methods rely on a rectification network, which is connected to the text recognition network. A portmanteau feature, inspired by the portmanteau word, is a feature containing information from both the original text image and the rectified image. The proposed method is examined on 6 benchmarks and compared with 13 state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-11-09T17:14:14Z)
• Pure Transformer with Integrated Experts for Scene Text Recognition [11.089203218000854]
  Scene text recognition (STR) involves the task of reading text in cropped images of natural scenes. Recent times, the transformer architecture is being widely adopted in STR as it shows strong capability in capturing long-term dependency. This work proposes the use of a transformer-only model as a simple baseline which outperforms hybrid CNN-transformer models.
  arXiv  Detail & Related papers  (2022-11-09T15:26:59Z)
• DPText-DETR: Towards Better Scene Text Detection with Dynamic Points in Transformer [94.35116535588332]
  Transformer-based methods, which predict polygon points or Bezier curve control points to localize texts, are quite popular in scene text detection. However, the used point label form implies the reading order of humans, which affects the robustness of Transformer model. We propose DPText-DETR, which directly uses point coordinates as queries and dynamically updates them between decoder layers.
  arXiv  Detail & Related papers  (2022-07-10T15:45:16Z)
• Few Could Be Better Than All: Feature Sampling and Grouping for Scene Text Detection [47.820683360286786]
  We present a transformer-based architecture for scene text detection. We first select a few representative features at all scales that are highly relevant to foreground text. As each feature group corresponds to a text instance, its bounding box can be easily obtained without any post-processing operation.
  arXiv  Detail & Related papers  (2022-03-29T04:02:31Z)
• Arbitrary Shape Text Detection using Transformers [2.294014185517203]
  We propose an end-to-end trainable architecture for arbitrary-shaped text detection using Transformers (DETR) At its core, our proposed method leverages a bounding box loss function that accurately measures the arbitrary detected text regions' changes in scale and aspect ratio. We evaluate our proposed model using Total-Text and CTW-1500 datasets for curved text, and MSRA-TD500 and ICDAR15 datasets for multi-oriented text.
  arXiv  Detail & Related papers  (2022-02-22T22:36:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.