Detecting and reading text in natural scenes

By Xiangrong Chen, Alan L. Yuille. Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004., 2004

769 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/76548769a142f858acf9d32e9bc4a2c5445fc9de

How researchers see this paper

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

1. Cong Yao
2. Xiang Bai
3. Andrea Vedaldi
4. Andrew Zisserman
5. Chunhua Shen
6. Minghui Liao
7. Yu Qiao
8. Luc Van Gool

Citations in the corpus

• Large-Lexicon Attribute-Consistent Text Recognition in Natural Images (2012, background): “morphological analysis [5], belief propagation in secondorder random fields [6], maximally stable regions [3], and pictorial structures [1].”
• A robust arbitrary text detection system for natural scene images (2014, methodology): “Chen and Yuille (2004) extracted 79 features for the text region given by a classifier and the method uses an adaptive binarization method to classify text and non-text pixels. Yi and Tian (2011) proposed a partitioning method using gradient and color information of pixels. It then uses features at ”
• Detecting Curve Text in the Wild: New Dataset and New Solution (2017, unknown): “.0 6.7 - CTPN [32] 53.8 60.4 56.9 59.4 54.3 56.7 37.7 34.1 35.8 7.14 EAST [38] 49.1 78.7 60.4 57.5 71.0 63.6 29.9 40.9 34.6 21.2 DMPNet [21] 56.0 69.9 62.2 61.7 63.9 62.7 39.3 35.5 37.3 12.3 AdaBoost [2] 4.4 6.7 5.3 - - - - - - - CTD (ours) 65.2 74.3 69.5 60.3 67.3 63.5 73.9 52.9 61.6 15.2 CTD + TLO”
• A Hybrid Approach to Detect and Localize Texts in Natural Scene Images (2011, methodology): “To speed up text detection, Chen and Yuille [5] proposed a fast text detector using a cascade AdaBoost classifier, whose weak learners are selected from a feature pool containing gray-level, gradient and edge features.”
• TextBoxes++: A Single-Shot Oriented Scene Text Detector (2018, methodology): “An algorithm based on AdaBoost is proposed in [31].”
• Text Detection and Recognition in Imagery: A Survey (2015, background): “They are combined with such classifiers as artificial neural networks [14], [16] or Adaboost [28], [68] to perform sliding window based text localization.”
• Robust Scene Text Detection with Convolution Neural Network Induced MSER Trees (2014, methodology): “The sliding-window based methods detect text information by sliding a sub-window in multiple scales through all locations of an image [11,3,9,28,29,18,1].”
• End-to-end scene text recognition (2011, background): “Adopting this approach opens the door for real world scene text recognition to benefit from the rapid advances that have been taking place in object recognition.”
• Supporting blind photography (2011, methodology): “%) had used a camera (including those on cell phones) recently.”
• Deep Features for Text Spotting (2014, methodology): “Text spotting in natural images is usually divided into two tasks [12]: text detection, and word recognition.”
• Detecting text in natural scenes with stroke width transform (2010, methodology): “Several prev algorithms [3, 18, 19] rely on class regions and therefore are not segmentation mask required for subse method carries enough information segmentation and so a good mask is r detected text.”
• Cascaded Segmentation-Detection Networks for Text-Based Traffic Sign Detection (2018, methodology): “Chen and Yuille [32] propose a fast text detector by using a strong AdaBoost classifier trained on a”
• Multi-oriented Text Detection with Fully Convolutional Networks (2016, methodology): “sliding windows [8, 25, 3, 24, 17] and connected component [16, 6, 4, 32, 28] have become mainstream in this specific domain.”
• Text Localization in Real-World Images Using Efficiently Pruned Exhaustive Search (2011, background): “Methods in the first category [2], [3] use a window which is moved over the image and the presence of text is estimated on the basis of local image features.”
• Text String Detection from Natural Scenes by Structure-based Partition and Grouping (2011, methodology): “Different from rule-based text detection as the above algorithms, Chen et al. [ 5 ] and Ho et al. [9] adopted Adaboost learning methods by using text features to establish the corresponding classifiers.”