Scene text detection and recognition: recent advances and future trends

By Yingying Zhu, Cong Yao, Xiang Bai. 2015

388 citations recorded by the source corpus.

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. Luc Van Gool
6. Dacheng Tao
7. Yu Qiao
8. Shuicheng Yan

In Media Technology

1. Cong Yao
2. Xiang Bai
3. Minghui Liao
4. Xin He
5. Shangbang Long
6. Lianwen Jin
7. Pengyuan Lyu
8. Yuliang Liu

Citations in the corpus

• All You Need Is Boundary: Toward Arbitrary-Shaped Text Spotting (2019, background): “Due to the page limit, we can not detail the works about scene text detection and recognition which are referred to (Long, He, and Yao 2018; Zhu, Yao, and Bai 2016).”
• Towards End-to-End Text Spotting with Convolutional Recurrent Neural Networks (2017, background): “Although significant progress has been made recently based on Deep Neural Network (DNN) techniques, it is still an open problem [36].”
• Traffic sign detection and recognition using fully convolutional network guided proposals (2016, neutral): “A large number of novel ideas and effective methods have been proposed [7 – 10, 12, 13, 16, 17, 21, 26 – 40 ].”
• Cascaded Segmentation-Detection Networks for Text-Based Traffic Sign Detection (2018, neutral): “can be found in [30].”
• Robust Scene Text Recognition with Automatic Rectification (2016, neutral): “Comprehensive surveys have been given in [40, 44].”
• Automatic discrimination of text and non-text natural images (2015, background): “However, majority of the existing works have focused on document images [6], [7], while those concerned with natural images mainly tackle tasks like text detection and recognition [8]–[13], rather the task of text/non-text distinction.”
• Recognizing Text-Based Traffic Guide Panels with Cascaded Localization Network (2016, methodology): “Although several general scene text detection and recognition methods [1,2,3] have been developed to localize and recognize the text information in the natural scenes, most of these methods used exhaustive manner such as sliding window to search for all possible regions containing text information a”
• Integrating Scene Text and Visual Appearance for Fine-Grained Image Classification (2017, background): “With the recent developments in text detection and recognition in the wild [4]–[7], it has been shown that textual cues are very beneficial to fine-grained classification, especially in the classification of business places such as bakery, cafe and bookstore [8].”
• Symmetry-based text line detection in natural scenes (2015, neutral): “For comprehensive surveys, refer to [19, 44, 50].”
• Deep Matching Prior Network: Toward Tighter Multi-oriented Text Detection (2017, background): “Therefore, the mainstream of text detection meth-ods always focused on the structure of individual characters and the relationships between characters [40], e.g . connected component based methods [38, 27, 22].”
• Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes (2018, background): “In scene text recognition systems, text detection plays an important role [59].”
• Object Detection in 20 Years: A Survey (2019, methodology): “nd 2) text recognition. The existing text detection methods can be divided into two groups: “step-wise detection” and “integrated detection”. We refer readers to the following survey for more details [338, 339]. Step-wise detection vs integrated detection Step-wise detection methods [340, 341] cons”
• EAST: An Efficient and Accurate Scene Text Detector (2017, background): “Comprehensive reviews and detailed analyses can be found in survey papers [50, 35, 43].”
• Multi-oriented Scene Text Detection via Corner Localization and Region Segmentation (2018, background): “In the past few years, scene text detection has been widely studied [58, 11, 6, 53, 21, 46, 56, 40, 45] and has achieved obvious progresses recently, with the rapid development of general object detection and semantic segmentation.”
• Scene Text Detection and Recognition: The Deep Learning Era (2018, background): “scene text detection and recognition (Zhu et al., 2016) or PhotoOCR (Bissacco et al.”
• TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes (2018, neutral): “scene text detection and recognition [48].”
• Multi-oriented Text Detection with Fully Convolutional Networks (2016, background): “Comprehensive surveys for scene text detection and recognition can be referred to [30, 36].”
• A Multi-Object Rectified Attention Network for Scene Text Recognition (2019, background): “Zhu et al. [57] and Ye et al. [53] have provided an overview of the major advances in the field of scene text detection and recognition.”
• Symmetry-Constrained Rectification Network for Scene Text Recognition (2019, background): “Scene text reading [60, 32, 59, 54, 53, 36, 35] is an important, active research area in computer vision, which can be applied to a wide range of real-world applications, such as self-driving cars, assistant position systems, and guide board recognition [43].”