Large-Lexicon Attribute-Consistent Text Recognition in Natural Images

By Tatiana G. Novikova, Olga Barinova, Pushmeet Kohli, Victor S. Lempitsky. 2012

127 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Natural Language Processing

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

In Natural Language Processing

Citations in the corpus

Deep Structured Output Learning for Unconstrained Text Recognition (2014, methodology): “We follow the standard evaluation protocol defined by Wang et al. (2011) and perform recognition on the words containing only alphanumeric characters and at least three characters. The test set of 860 cropped word images is referred to as IC03. The lexicon of all test words is IC03-Full (563 words),”
Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition (2014, methodology): “In contrast to these approaches based on character classification, the work by [7, 17, 21, 24] instead uses the notion of holistic word recognition.”
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.”
Whole is Greater than Sum of Parts: Recognizing Scene Text Words (2013, methodology): “From the results, we see that the proposed holistic word matching based scheme outperforms not only our earlier work [12], but also many recent works as [14], [18], [19] on the SVT dataset.”
Recognizing Text with Perspective Distortion in Natural Scenes (2013, methodology): “Following [1, 2], the context information is utilized through lexicons.”
Deep Features for Text Spotting (2014, background): “In [36], Novikova combines both visual and lexicon consistency into a single probabilistic model.”
A Unified Framework for Multioriented Text Detection and Recognition (2014, methodology): “In order to correct errors in character recognition, language prior and context information (e.g. n-gram statistics [20], [27]– [29], lexicon or dictionary [18], [21], [30], [31]) are usually employed.”
Scene text detection and recognition: recent advances and future trends (2015, background): “[14] 2012 can recognize words in complex natural images rely on large lexicon sensitive to blur and occlusion”
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.”
Recursive Recurrent Nets with Attention Modeling for OCR in the Wild (2016, unknown): “CRFs) on top of the output prediction of each character position as in [31, 32, 34].”
Text Detection and Recognition in Imagery: A Survey (2015, methodology): “Novikova [165] 2012 Large-lexicon driven recognition, weighted finitestate transducers based inference ICDAR’03 1156/90k 0.”
Label embedding for text recognition (2013, methodology): “Experiments are performed on two challenging datasets (one of license plates and one of scene text) and show that the proposed method is competitive with standard bottom-up approaches to text recognition.”
Symmetry-Constrained Rectification Network for Scene Text Recognition (2019, methodology): “A popular pipeline of traditional methods [10, 50, 49, 51, 38, 37, 39, 55, 4] is in the bottom-up architecture.”