Corpus ID: 17991431

Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networks

@article{Goodfellow2014MultidigitNR,
  title={Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networks},
  author={Ian J. Goodfellow and Yaroslav Bulatov and J. Ibarz and Sacha Arnoud and V. Shet},
  journal={CoRR},
  year={2014},
  volume={abs/1312.6082}
}
  • Ian J. Goodfellow, Yaroslav Bulatov, +2 authors V. Shet
  • Published 2014
  • Computer Science
  • CoRR
  • Abstract: Recognizing arbitrary multi-character text in unconstrained natural photographs is a hard problem. In this paper, we address an equally hard sub-problem in this domain viz. recognizing arbitrary multi-digit numbers from Street View imagery. Traditional approaches to solve this problem typically separate out the localization, segmentation, and recognition steps. In this paper we propose a unified approach that integrates these three steps via the use of a deep convolutional neural… CONTINUE READING
    485 Citations
    Recognizing Characters From Google Street View Images
    • 1
    • PDF
    Reading numbers in natural scene images with convolutional neural networks
    • Q. Guo, Jun Lei, D. Tu, Guohui Li
    • Computer Science
    • Proceedings 2014 IEEE International Conference on Security, Pattern Analysis, and Cybernetics (SPAC)
    • 2014
    • 4
    Optical character recognition using deep recurrent attention model
    • 1
    Sequence recognition of natural scene house number based on convolutional neural network
    Noisy Character Recognition Using Deep Convolutional Neural Networks
    MDig : Multi-digit Recognition using Convolutional Nerual Network on Mobile
    • 3
    • PDF
    Hybrid CNN-HMM Model for Street View House Number Recognition
    • 5
    • PDF
    Assessing four Neural Networks on Handwritten Digit Recognition Dataset (MNIST)
    • 10
    • PDF
    A Further Step to Perfect Accuracy by Training CNN with Larger Data
    • 19
    • PDF

    References

    SHOWING 1-10 OF 19 REFERENCES
    Reading Digits in Natural Images with Unsupervised Feature Learning
    • 2,445
    • PDF
    Convolutional neural networks applied to house numbers digit classification
    • 384
    • PDF
    Gradient-based learning applied to document recognition
    • 25,503
    • PDF
    Deep Neural Networks for Object Detection
    • 938
    • PDF
    What is the best multi-stage architecture for object recognition?
    • 1,803
    • Highly Influential
    • PDF
    Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
    • 11,975
    • PDF
    Visualizing and Understanding Convolutional Networks
    • 8,595
    • PDF
    End-to-End Text Recognition with Hybrid HMM Maxout Models
    • 91
    • PDF
    Large Scale Distributed Deep Networks
    • 2,439
    • PDF