Whole is Greater than Sum of Parts: Recognizing Scene Text Words

By Vibhor Goel, Anand Mishra, Alahari Karteek, C. V. Jawahar. 2013

98 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): “Goel et al. (2013) use whole word-image features to recognize words by comparing to simple black-and-white font-renderings of lexicon 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, methodology): “[25] use whole word sub-image features to recognise words by comparing to simple black-and-white font-renderings of lexicon words.”
Text Detection and Recognition in Imagery: A Survey (2015, background): “Goel [179] 2013 Holistic recognition by gradient based features and dynamic matching ICDAR’03 50 0.”
Focusing Attention: Towards Accurate Text Recognition in Natural Images (2017, unknown): “[6] − − − 77.”
An End-to-End Trainable Neural Network for Image-Based Sequence Recognition and Its Application to Scene Text Recognition (2015, unknown): “[37] - - 77.”
Deep Features for Text Spotting (2014, methodology): “On the SVT dataset, we achieve an accuracy of 86.1%, which while 4.3% oﬀ state-of-the-art, improves on the next best result [19] by 8.8%.”
Strokelets: A Learned Multi-scale Representation for Scene Text Recognition (2014, unknown): “Whole [1] 77.”
Robust Scene Text Recognition with Automatic Rectification (2016, unknown): “[11] - - - 77.”
Recursive Recurrent Nets with Attention Modeling for OCR in the Wild (2016, unknown): “[8] 77.”
PhotoOCR: Reading Text in Uncontrolled Conditions (2013, unknown): “[9] 77.”
TextProposals: A text-specific selective search algorithm for word spotting in the wild (2016, background): “Holistic word recognition methods [2, 3, 1] have demonstrated great success in difficult tasks like pre-segmented word recognition, end-to-end word spotting, and text based retrieval.”
Scene text detection and recognition: recent advances and future trends (2015, unknown): “48 Discriminative Feature Pooling [33] 76 88 CNN [73] 84 90 Whole [92] 89.”
Supervised mid-level features for word image representation (2014, background): “Compared to methods that do not use millions of training samples [20, 9, 41, 13] , our results are significantly better.”
Reading Scene Text in Deep Convolutional Sequences (2015, result): “They are compared systematically to recent results achieved by mid-level features [33, 20, 27, 25, 22], deep neural networks systems [18, 2, 32] and whole image based representations [1, 8], along with discussions on their advantages and disadvantages.”