A Hybrid Approach to Detect and Localize Texts in Natural Scene Images

By Yi-Feng Pan, Xinwen Hou, Chenglin Liu. IEEE Transactions on Image Processing, 2011

441 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/a79f43246bed540084ca2d1fcf99a68c69820747

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. Yu Qiao
4. Chunhua Shen
5. Luc Van Gool
6. Minghui Liao
7. Dacheng Tao
8. Andrew Zisserman

Citations in the corpus

• A Fast Uyghur Text Detector for Complex Background Images (2018, background): “At the same time, whether the window is a text region or not, it can be distinguished with a classifier, such as AdaBoost [13], [14], random forest [15], support vector machine (SVM) [16] or convolutional neural network (CNN) [17]–[19].”
• Scene text detection and recognition: recent advances and future trends (2015, methodology): “Hybrid methods [27, 54] are a combination of texture based methods and component based methods, which make use of the advantages of these two types methods.”
• Multi-oriented Text Detection with Fully Convolutional Networks (2016, methodology): “However, most text detection methods focus on detecting horizontal or near-horizontal text mainly in two ways: 1) localizing the bounding boxes of words [4, 3, 17, 15, 18, 33, 5, 6], 2) combining detection and recognition procedures into an end-to-end text recognition method [8, 28].”
• Symmetry-based text line detection in natural scenes (2015, methodology): “To better distinguish text and non-text, we employ appearance feature, as it has been widely used in previous works [5, 29].”
• A robust arbitrary text detection system for natural scene images (2014, methodology): “It has been shown that the combination of stroke width with gradient magnitude proposed in Pan et al. (2011) for text detection is good for classifying text and non-text components.”
• Cascaded Segmentation-Detection Networks for Text-Based Traffic Sign Detection (2018, methodology): “[41] present a method that extract text components from the multi-scale probability maps.”
• ICDAR 2011 Robust Reading Competition Challenge 2: Reading Text in Scene Images (2011, background): “Research on scene text detection and recognition already started in mid-90s [1], [2] and since then has seen a substantial amount of growth with a large number of approaches published in the last decade [3], [4], [5], [6], [7].”
• A Unified Framework for Multioriented Text Detection and Recognition (2014, methodology): “Driven by the wide range of potential applications, scene text detection and recognition have been important research topics for decades [7], [8], [35]–[41] and have recently seen a surge in research efforts in the computer vision community [9]–[14], [17], [18], [20], [21], [26], [42].”
• TextBoxes: A Fast Text Detector with a Single Deep Neural Network (2016, neutral): “…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 2014).”
• Detecting texts of arbitrary orientations in natural images (2012, background): “These two shortcomings are also pointed out in [23, 29].”
• Text-Attentional Convolutional Neural Network for Scene Text Detection (2015, methodology): “The sliding-window methods detect text information by moving a multi-scale sub-window through all possible locations in an image [8], [4], [2], [12], [13], [14], [15], [16], [17].”
• TextBoxes++: A Single-Shot Oriented Scene Text Detector (2018, background): “character/word candidate generation [6]–[8], candidate filtering [8], and grouping [9].”
• Robust Seed Localization and Growing with Deep Convolutional Features for Scene Text Detection (2015, methodology): “Many existing methods are devoted to the first stage, which can be further categorized into two groups: the exhaustive search based methods [1, 10, 16, 18] and the selective search based methods [2, 12, 13, 6, 14, 21, 3, 9].”
• Deep Direct Regression for Multi-oriented Scene Text Detection (2017, background): “Most scene text detection methods [26] [21] [8] [1] [17] treat text as a composite of characters, so they first localize character or components candidates and then group them into a word or text line.”
• Text Detection and Recognition in Imagery: A Survey (2015, methodology): “with statistical models [109], [138], [182], e.”
• Strokelets: A Learned Multi-scale Representation for Scene Text Recognition (2014, neutral): “Original images are from [26].”