Open AccessPosted Content
Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition
Reads0
Chats0
TLDR
This work presents a framework for the recognition of natural scene text that does not require any human-labelled data, and performs word recognition on the whole image holistically, departing from the character based recognition systems of the past.Abstract:
In this work we present a framework for the recognition of natural scene text. Our framework does not require any human-labelled data, and performs word recognition on the whole image holistically, departing from the character based recognition systems of the past. The deep neural network models at the centre of this framework are trained solely on data produced by a synthetic text generation engine -- synthetic data that is highly realistic and sufficient to replace real data, giving us infinite amounts of training data. This excess of data exposes new possibilities for word recognition models, and here we consider three models, each one "reading" words in a different way: via 90k-way dictionary encoding, character sequence encoding, and bag-of-N-grams encoding. In the scenarios of language based and completely unconstrained text recognition we greatly improve upon state-of-the-art performance on standard datasets, using our fast, simple machinery and requiring zero data-acquisition costs.read more
Citations
More filters
Book ChapterDOI
Towards Accurate Handwritten Word Recognition for Hindi and Bangla
TL;DR: This work demonstrates an end-to-end trainable CNN-RNN hybrid architecture which takes inspirations from recent advances of using residual blocks for training convolutional layers, along with the inclusion of spatial transformer layer to learn a model invariant to geometric distortions present in handwriting.
Posted Content
Separating Content from Style Using Adversarial Learning for Recognizing Text in the Wild
TL;DR: This work proposes an adversarial learning framework for the generation and recognition of multiple characters in an image, which consists of an attention-based recognizer and a generative adversarial architecture, and designs an interactive joint training scheme to tackle the issue of lacking paired training samples.
Posted Content
Rethinking Text Segmentation: A Novel Dataset and A Text-Specific Refinement Approach
TL;DR: This work proposes TextSeg, a large-scale fine-annotated text dataset with six types of annotations, and introduces Text Refinement Network (TexRNet), a novel text segmentation approach that adapts to the unique properties of text, e.g. non-convex boundary, diverse texture, etc., which often impose burdens on traditional segmentation models.
Posted Content
AutoSTR: Efficient Backbone Search for Scene Text Recognition
TL;DR: This work designs a domain-specific search space for STR, which contains both choices on operations and constraints on the downsampling path, and proposes a two-step search algorithm, which decouples operations and downsampled path, for an efficient search in the given space.
Proceedings ArticleDOI
Compression of fully-connected layer in neural network by Kronecker product
TL;DR: In this article, the weight matrices of the fully-connected layers are approximated by linear combinations of multiple Kronecker products of smaller matrices, which can achieve 10x reduction of number of parameters with less than 1% drop in accuracy.
References
More filters
Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Journal ArticleDOI
Gradient-based learning applied to document recognition
Yann LeCun,Léon Bottou,Léon Bottou,Yoshua Bengio,Yoshua Bengio,Yoshua Bengio,Patrick Haffner +6 more
TL;DR: In this article, a graph transformer network (GTN) is proposed for handwritten character recognition, which can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters.
Posted Content
Improving neural networks by preventing co-adaptation of feature detectors
TL;DR: The authors randomly omits half of the feature detectors on each training case to prevent complex co-adaptations in which a feature detector is only helpful in the context of several other specific feature detectors.
Journal ArticleDOI
DRC: a dual route cascaded model of visual word recognition and reading aloud.
TL;DR: The DRC model is a computational realization of the dual-route theory of reading, and is the only computational model of reading that can perform the 2 tasks most commonly used to study reading: lexical decision and reading aloud.
Proceedings Article
OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks
TL;DR: In this article, a multiscale and sliding window approach is proposed to predict object boundaries, which is then accumulated rather than suppressed in order to increase detection confidence, and OverFeat is the winner of the ImageNet Large Scale Visual Recognition Challenge 2013.
Related Papers (5)
An End-to-End Trainable Neural Network for Image-Based Sequence Recognition and Its Application to Scene Text Recognition
Baoguang Shi,Xiang Bai,Cong Yao +2 more