Strokelets: A Learned Multi-scale Representation for Scene Text Recognition

By Cong Yao, Xiang Bai, Baoguang Shi. 2014

308 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

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

Citations in the corpus

Deep Structured Output Learning for Unconstrained Text Recognition (2014, neutral): “el et al. (2013) 89.7 - - - 77.3 - - - - Bissacco et al. (2013) - - - - 90.4 78.0 87.6 - - Alsharif & Pineau (2014) 93.1 88.6 85.1 - 74.3 - - - - Almaz´an et al. (2014) - - - - 89.2 - - 91.2 82.1 Yao et al. (2014) 88.5 80.3 - - 75.9 - - 80.2 69.3 Jaderberg et al. (2014c) 96.2 91.5 - - 86.1 - - -”
Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition (2014, neutral): “57.5 Wang & Wu [27] 90.0 84.0 - 70.0 - - - - Goel [7] 89.7 - - 77.3 - - - - PhotoOCR [3] - - - 90.4 78.0 87.6 - - Alsharif [2] 93.1 88.6 85.1 74.3 - - - - Almazan [1] - - - 89.2 - - 91.2 82.1 Yao [29] 88.5 80.3 - 75.9 - - 80.2 69.3 Jaderberg [11] 96.2 91.5 - 86.1 - - - - Gordo [9] - - - 90.7 - -”
Reading Text in the Wild with Convolutional Neural Networks (2014, background): “2013), text recognition (Almazán et al. 2014;Bissacco et al. 2013; Jaderberg et al. 2014;Mishra et al. 2012; Novikova et al. 2012; Rath and Manmatha 2007; Yao et al. 2014), or on combining both in end-to-end systems (Alsharif and Pineau 2014; Gordo 2014; Jaderberg et al.”
Focusing Attention: Towards Accurate Text Recognition in Natural Images (2017, background): “Early works mainly develop bottom-up approaches: first detecting characters one by one by sliding window [29, 30], connected components [21] or Hough voting [32], then integrating these characters into the output text.”
Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes (2018, background): “Scene text recognition [53, 46] aims at decoding the detected or cropped image regions into character sequences.”
EAST: An Efficient and Accurate Scene Text Detector (2017, background): “Numerous inspiring ideas and effective approaches [5, 25, 26, 24, 27, 37, 11, 12, 7, 41, 42, 31] have been investigated.”
Scene text detection and recognition: recent advances and future trends (2015, methodology): “[7] 2014 can recognize words in complex natural images can learn character parts from training data insensitive to blur, occlusion, font variation inefficient”
Show, Attend and Read: A Simple and Strong Baseline for Irregular Text Recognition (2018, background): “Early approaches mainly work in a bottom-up fashion (Wang, Babenko, and Belongie 2011; Mishra, Ala-hari, and Jawahar 2012b; Phan et al. 2013; Yao et al. 2014), in which individual characters are detected ﬁrstly via sliding window or connected components, and then integrated into a word by dynamic…”
Recursive Recurrent Nets with Attention Modeling for OCR in the Wild (2016, methodology): “Some early attempts [26, 53, 10] try to learn local mid-level”
Scene Text Detection and Recognition: The Deep Learning Era (2018, background): “Shi et al. [126] and Yao et al. [153] proposed character segments based recognition algorithms.”
TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes (2018, background): “Numerous innovative works [39, 29, 47, 17, 10, 46, 30, 36, 6, 9, 34, 22, 28, 40, 31] are proposed, achieving excellent performances on standard benchmarks.”
Reading Scene Text in Deep Convolutional Sequences (2015, background): “This problem includes two sub tasks, namely text detection [16, 34, 35, 15, 24] and text-line/word recognition[18, 1, 17, 4, 33].”
ESIR: End-To-End Scene Text Recognition via Iterative Image Rectification (2018, methodology): “Different scene character detection and recognition methods have been reported by using sliding window [43, 42], connected components [31], extremal regions [32], Hough voting [47], co-occurrence histograms [41], etc.”
Automatic discrimination of text and non-text natural images (2015, background): “Different from conventional approaches related to textual information understanding, which are usually concerned with text detection or recognition [4], we tackle in this paper the problem of text image discrimination.”
A Unified Framework for Multioriented Text Detection and Recognition (2014, background): “As stated in [22], in conventional end-to-end scene text recognition systems [10], [21], decisions of different components in the pipeline are sequential and isolated, which makes it impossible to exploit feedback information between different components.”
A Multi-Object Rectified Attention Network for Scene Text Recognition (2019, background): “…by a neural network become dominant with respect to the hand crafted features, such as the connected components [33], strokelet generation [52], histogram of oriented gradients descriptors [10, 44], tree-structured models [43], semi-markov conditional random ﬁelds [40] and generative…”
Supervised mid-level features for word image representation (2014, methodology): “[41], which learns Strokelets, a mid-level representation that can be understood as “parts” of characters.”
Symmetry-based text line detection in natural scenes (2015, background): “Though extensively studied in the past decade [5, 7, 25, 35, 41, 27, 3, 42, 12], detecting and reading texts in natural scenes are still difficult tasks.”