Detecting texts of arbitrary orientations in natural images

By Cong Yao, Xiang Bai, Yi Ma, Zhuowen Tu. 2012 IEEE Conference on Computer Vision and Pattern Recognition, 2012

876 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/5372150dabf77a75e88d23f13252e92764430b33

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. Chunhua Shen
3. Luc Van Gool
4. Dacheng Tao
5. Cong Yao
6. Yu Qiao
7. Ming-Hsuan Yang
8. Xiaogang Wang

Citations in the corpus

• Real-Time Scene Text Detection With Differentiable Binarization and Adaptive Scale Fusion (2022, methodology): “The comparisons of several recent scene text detection methods on the MSRA-TD500 dataset [59], in terms of both accuracy (F-measure) and speed.”
• Structured Multimodal Attentions for TextVQA (2020, methodology): “The SBD model is pretrained on a 60k dataset, which consists of 30, 000 images from LSVT [40] training set, 10, 000 images from MLT 2019 [31] training set, 5, 603 images from ArT [10] which contains all the images of SCUT-CTW1500 [27] and Total-text [9,11], and the rest of 14, 859 images are selecte”
• Recognizing Text with Perspective Distortion in Natural Scenes (2013, methodology): “The typical features used for detection are stroke widths [9, 10], Maximally Stable Extremal Regions (MSER) [11, 12] and HOG [1].”
• DOTA: A Large-Scale Dataset for Object Detection in Aerial Images (2017, methodology): “An option for annotating oriented objects is θ-based oriented bounding box which is adopted in some text detection benchmarks [37], namely (xc, yc, w, h, θ), where θ denotes the angle from the horizontal direction of the standard bounding box.”
• Total-Text: toward orientation robustness in scene text detection (2019, background): “Well-known public datasets such as ICDAR’03, ’11, ’13 [1] (ICDARs from here on), and MSRA-TD500 [2] have played significant roles in initiating the momentum of scene text-related research.”
• Multi-oriented Text Detection with Fully Convolutional Networks (2016, methodology): “The MSRA-TD500 dataset introduced in [29], is a multi-orientation text dataset including 300 training images and 200 testing images.”
• Scene text detection and recognition: recent advances and future trends (2015, methodology): “[12] 2012 can detect texts of different orientations can handle multilingual texts reasonably fast rely on manually defined rules”
• TextOCR: Towards large-scale end-to-end reasoning for arbitrary-shaped scene text (2021, methodology): “4 11 MSRA-TD500 [61] 300 200 – – – 12 CTW-1500 [34] 1000 500 – – – 13 COCO-Text [57] 18895 4416 61793 13910 3.”
• Scene Text Detection and Recognition: The Deep Learning Era (2018, methodology): “It achieves state-of-theart performance on several curved text datasets as well as more widely used ones, e.g. ICDAR 2015 (Karatzas et al. 2015) and MSRA-TD 500 (Tu et al. 2012).”
• Robust Scene Text Detection with Convolution Neural Network Induced MSER Trees (2014, background): “Stroke width transform (SWT) [7,31,10] and Maximally Stable Extremal Regions (MSERs) [16,23,24,22,34] are two representative low-level filters applied for scene text detection with great success.”
• Detecting Curve Text in the Wild: New Dataset and New Solution (2017, background): “For example, horizontal rectangular labels in ICDAR 2013 “Focus Scene Text” [17] and SVT [34]; rotated rectangular labels in MSRA-TD500 [35] and USTB-SV1K [37]; four points labels in ICDAR 2015 “Incidental Text” [16], RCTW-17 [30] and recent MLT competition dataset [13].”
• Scene Text Localization and Recognition with Oriented Stroke Detection (2013, background): “The second, recently more popular approach [4, 13, 11, 19, 12, 15] is based on localizing individual characters as connected components using local properties of an image (color, intensity, stroke-width, etc.”
• TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes (2018, background): “For experiments on ICDAR 2015 and MSRA-TD500, we fit a minimum bounding rectangle based on the output text area of our method.”
• TextBoxes: A Fast Text Detector with a Single Deep Neural Network (2016, neutral): “Based on a basic detection target, previous methods for text detection can be roughly categorized into three categories: 1) Character-based: Individual characters are first detected and then grouped into words (Neumann and Matas 2012; Pan, Hou, and Liu 2011; Yao et al. 2012; Huang, Qiao, and Tang 20”
• An End-to-End TextSpotter with Explicit Alignment and Attention (2018, positive): “Recent approaches cast previous character-based text detection [14, 15, 11, 37] into direct text region estimation [24, 43, 42, 10, 8, 41, 38], which avoids multiple bottom-up post-processing steps by taking word or text-line as a whole detection unite.”
• Text-Attentional Convolutional Neural Network for Scene Text Detection (2015, methodology): “Our system is evaluated on the ICDAR 2005, 2011 and 2013 Robust Reading Competition benchmarks and the MSRA-TD500 database.”
• A robust arbitrary text detection system for natural scene images (2014, methodology): “The reported quantitative result in Table 5 shows that the proposed method achieves better recall, precision and F-measure compared to the method (Yao et al., 2012).”