Focusing Attention: Towards Accurate Text Recognition in Natural Images
Zhanzhan Cheng,Fan Bai,Yunlu Xu,Gang Zheng,Shiliang Pu,Shuigeng Zhou +5 more
- pp 5086-5094
Reads0
Chats0
TLDR
Zhang et al. as mentioned in this paper proposed Focusing Attention Network (FAN) which employs a focusing attention mechanism to automatically draw back the drifted attention. But the FAN method is not suitable for complex and low-quality images and it cannot get accurate alignment between feature areas and targets for such images.Abstract:
Scene text recognition has been a hot research topic in computer vision due to its various applications. The state of the art is the attention-based encoder-decoder framework that learns the mapping between input images and output sequences in a purely data-driven way. However, we observe that existing attention-based methods perform poorly on complicated and/or low-quality images. One major reason is that existing methods cannot get accurate alignments between feature areas and targets for such images. We call this phenomenon “attention drift”. To tackle this problem, in this paper we propose the FAN (the abbreviation of Focusing Attention Network) method that employs a focusing attention mechanism to automatically draw back the drifted attention. FAN consists of two major components: an attention network (AN) that is responsible for recognizing character targets as in the existing methods, and a focusing network (FN) that is responsible for adjusting attention by evaluating whether AN pays attention properly on the target areas in the images. Furthermore, different from the existing methods, we adopt a ResNet-based network to enrich deep representations of scene text images. Extensive experiments on various benchmarks, including the IIIT5k, SVT and ICDAR datasets, show that the FAN method substantially outperforms the existing methods.read more
Citations
More filters
Proceedings ArticleDOI
IterVM: Iterative Vision Modeling Module for Scene Text Recognition
Xiaojie Chu,Yongtao Wang +1 more
TL;DR: This paper newly proposes iterative vision modeling module (IterVM) to further improve the STR accuracy, and proposes a powerful scene text recognizer called IterNet, which achieves new state-of-the-art results on several public benchmarks.
Proceedings ArticleDOI
TextSRNet: Scene Text Super-Resolution Based on Contour Prior and Atrous Convolution
TL;DR: Zhang et al. as discussed by the authors proposed a new scene text super-resolution network called TextSRNet to get fine character details by adopting the segmentation maps of scene text images as the prior knowledge of character contours and embedding it into the proposed textSRNet.
Book ChapterDOI
Text-Conditioned Character Segmentation for CTC-Based Text Recognition
TL;DR: This article proposed Text-conditioned Character Segmentation (TCSeg) to improve segmentation accuracy by segmentation-free text recognition without affecting recognition accuracy, and also proposed Overlap and Skip Error Suppression (OSESup) to suppress unintuitive errors.
Posted Content
Revisiting Classification Perspective on Scene Text Recognition
TL;DR: CSTR as mentioned in this paper revisited classification perspective that models scene text recognition as an image classification problem and achieved state-of-the-art performance on six public benchmarks including regular text, irregular text and irregular text.
Proceedings ArticleDOI
Text Recognition in Real Scenarios with a Few Labeled Samples
TL;DR: Zhang et al. as mentioned in this paper proposed a few-shot adversarial sequence domain adaptation (FASDA) approach to build sequence adaptation between the synthetic source domain (with many synthetic labeled samples) and a specific target domain with only some or a few real labeled samples.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Journal ArticleDOI
Learning representations by back-propagating errors
TL;DR: Back-propagation repeatedly adjusts the weights of the connections in the network so as to minimize a measure of the difference between the actual output vector of the net and the desired output vector, which helps to represent important features of the task domain.
Proceedings Article
Neural Machine Translation by Jointly Learning to Align and Translate
TL;DR: It is conjecture that the use of a fixed-length vector is a bottleneck in improving the performance of this basic encoder-decoder architecture, and it is proposed to extend this by allowing a model to automatically (soft-)search for parts of a source sentence that are relevant to predicting a target word, without having to form these parts as a hard segment explicitly.
Proceedings Article
Sequence to Sequence Learning with Neural Networks
TL;DR: The authors used a multilayered Long Short-Term Memory (LSTM) to map the input sequence to a vector of a fixed dimensionality, and then another deep LSTM to decode the target sequence from the vector.
Proceedings ArticleDOI
Caffe: Convolutional Architecture for Fast Feature Embedding
Yangqing Jia,Evan Shelhamer,Jeff Donahue,Sergey Karayev,Jonathan Long,Ross Girshick,Sergio Guadarrama,Trevor Darrell +7 more
TL;DR: Caffe provides multimedia scientists and practitioners with a clean and modifiable framework for state-of-the-art deep learning algorithms and a collection of reference models for training and deploying general-purpose convolutional neural networks and other deep models efficiently on commodity architectures.