Symmetry-based text line detection in natural scenes

By Zheng Zhang, Wei Shen, Cong Yao, Xiang Bai. 2015

273 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. Luc Van Gool
5. Yu Qiao
6. Dacheng Tao
7. Minghui Liao
8. Chen Change Loy

In Media Technology

1. Cong Yao
2. Xiang Bai
3. Minghui Liao
4. Xin He
5. Shangbang Long
6. Chunhua Shen
7. Pengyuan Lyu
8. Baoguang Shi

Citations in the corpus

• Synthetic Data for Text Localisation in Natural Images (2016, neutral): “Zhang [47] - - - - - - - - - - - - 80 84 76 80 88 74 - - -”
• Text-Attentional Convolutional Neural Network for Scene Text Detection (2015, methodology): “[4] proposed a symmetry-based text line detector that computes both symmetry and appearance features based on heuristic image properties.”
• Text/non-text image classification in the wild with convolutional neural networks (2017, background): “To precisely localize text in an image, algorithms like [4, 5, 6, 7, 8] typically require searching a large set of text-line or character candidates, or dense image patches.”
• TextBoxes++: A Single-Shot Oriented Scene Text Detector (2018, background): “The works in [21], [28]–[30] are such examples.”
• Rotation-Sensitive Regression for Oriented Scene Text Detection (2018, methodology): “Based on the representation of detection output, scene text detectors could be roughly divided into two categories: 1) Horizontal text detectors [49, 19, 11, 11, 44, 26] which detect words or text lines in terms of horizontal bounding boxes in the same way as general object detectors.”
• Detecting Text in Natural Image with Connectionist Text Proposal Network (2016, result): “We compare our performance against recently published results in [1, 28, 34].”
• Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes (2018, background): “A large number of methods have been proposed to detect scene text [7, 36, 37, 50, 19, 23, 54, 21, 47, 54, 56, 30, 52, 55, 34, 15, 48, 43, 57, 16, 35, 31].”
• Multi-oriented Scene Text Detection via Corner Localization and Region Segmentation (2018, unknown): “[55] 88.”
• Towards End-to-End Text Spotting with Convolutional Recurrent Neural Networks (2017, background): “We do not need to process the intermediate issues such as character grouping [35, 26] or text line separation [32], and thus avoid error accumulation.”
• EAST: An Efficient and Accurate Scene Text Detector (2017, methodology): “[47] made use of the local symmetry property of text and designed various features for text region detection.”
• Multi-oriented Text Detection with Fully Convolutional Networks (2016, methodology): “In addition, it is worth mentioning that both of the recent approaches [25, 8, 6] and our method, which used the deep convolutional neural network, have achieved superior performance over conventional approaches in several aspects: 1) learn a more robust component representation by pixel labeling wi”
• TextBoxes: A Fast Text Detector with a Single Deep Neural Network (2016, unknown): “For example, (Zhang et al. 2015) proposes to detect text lines utilizing their symmetric characteristics.”
• Total-Text: A Comprehensive Dataset for Scene Text Detection and Recognition (2017, background): “Such observation has inspired researchers to incorporate horizontal assumption [3]–[7] in solving the scene text detection problem.”
• Arbitrary Shape Scene Text Detection With Adaptive Text Region Representation (2019, background): “Sliding window based meth-ods [27, 32] move a multi-scale window over an image and classify the current patch as text or non-text.”
• Object Skeleton Extraction in Natural Images by Fusing Scale-Associated Deep Side Outputs (2016, background): “Extracting object skeletons directly from natural images is of broad interests to many real applications including object recognition/detection [4, 30], text recognition [36], road detection and blood vessel detection [29].”
• Object Detection in 20 Years: A Survey (2019, unknown): “emal Regions (MSER) segmentation [341] and morphological filtering [346]. Some domain knowledge, such as the symmetry of texts and the structures of strokes, also have been considered in these methods [340, 341, 347]. In recent years, researchers have paid more attention to the problem of text locali”
• Deep Direct Regression for Multi-oriented Scene Text Detection (2017, methodology): “SymmetryText [25] might be the first work that treats scene text detection as object detection.”