Arbitrary Shape Scene Text Detection With Adaptive Text Region Representation

By Xiaobing Wang, Yingying Jiang, Zhenbo Luo, Chenglin Liu, Hyunsoo Choi, Sungjin Kim. 2019

187 citations recorded by the source corpus.

Scene text detection attracts much attention in computer vision, because it can be widely used in many applications such as real-time text translation, automatic information entry, blind person assistance, robot sensing and so on. Though many methods have been proposed for horizontal and oriented texts, detecting irregular shape texts such as curved texts is still a challenging problem. To solve the problem, we propose a robust scene text detection method with adaptive text region representation. Given an input image, a text region proposal network is first used for extracting text proposals. Then, these proposals are verified and refined with a refinement network. Here, recurrent neural network based adaptive text region representation is proposed for text region refinement, where a pair of boundary points are predicted each time step until no new points are found. In this way, text regions of arbitrary shapes are detected and represented with adaptive number of boundary points. This gives more accurate description of text regions. Experimental results on five benchmarks, namely, CTW1500, TotalText, ICDAR2013, ICDAR2015 and MSRA-TD500, show that the proposed method achieves state-of-the-art in scene text detection.

Subfields: Computer Vision and Pattern Recognition, Media Technology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Xiang Bai
2. Cong Yao
3. Chunhua Shen
4. Minghui Liao
5. Xin He
6. Kai Chen
7. Shangbang Long
8. Tong He

In Media Technology

1. Cong Yao
2. Minghui Liao
3. Xiang Bai
4. Xin He
5. Shangbang Long
6. Zhaoyi Wan
7. Kai Chen
8. Chunhua Shen

Citations in the corpus

• All You Need Is Boundary: Toward Arbitrary-Shaped Text Spotting (2019, background): “In spite of predicting boundary points directly without post processing in (Wang et al. 2019), a recurrent neural network based network is time consuming for end-to-end task.”
• Real-time Scene Text Detection with Differentiable Binarization (2019, methodology): “Take two recent state-of-the-art methods for scene text detection as examples: PSENet (Wang et al. 2019a) proposed the post-processing of progressive scale expansion for improving the detection accuracies; Pixel embedding in (Tian et al. 2019) is used for clustering the pixels based on the segmentat”
• ABCNet: Real-Time Scene Text Spotting With Adaptive Bezier-Curve Network (2020, background): “Despite tremendous progress has been made recently [10, 42, 28, 36, 27, 43, 45, 41, 46, 14], detecting and recognizing text in the wild remains largely unsolved due to its diversity patterns in sizes, aspect ratios, font styles, perspective distortion, and shapes.”
• Scene Text Detection and Recognition: The Deep Learning Era (2018, methodology): “] 84.9 80.4 82.6 1.1 He et al. [49] 84 83 83 - Lyu et al. [100] 85.8 81.2 83.4 4.8 PixelLink [22] 85.5 82.0 83.7 3.0 Baek et al. [6] 89.8 84.3 86.9 8.6 Zhang et al. [175] 87.8 87.6 87.7 - Wang et al. [155] 89.2 86.0 87.6 - Tian et al. [143] 85.1 84.5 84.8 - TABLE 4: Detection on Total-Text. Method D”