A new unsupervised convolutional neural network model for Chinese scene text detection

Xiaohang Ren, Kai Chen, Xiaokang Yang, Yi Zhou, Jianhua He, Jun Sun

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)

Abstract

As one of the most popular deep learning models, convolution neural network (CNN) has achieved huge success in image information extraction. Traditionally CNN is trained by supervised learning method with labeled data and used as a classifier by adding a classification layer in the end. Its capability of extracting image features is largely limited due to the difficulty of setting up a large training dataset. In this paper, we propose a new unsupervised learning CNN model, which uses a so-called convolutional sparse auto-encoder (CSAE) algorithm pre-Train the CNN. Instead of using labeled natural images for CNN training, the CSAE algorithm can be used to train the CNN with unlabeled artificial images, which enables easy expansion of training data and unsupervised learning. The CSAE algorithm is especially designed for extracting complex features from specific objects such as Chinese characters. After the features of articficial images are extracted by the CSAE algorithm, the learned parameters are used to initialize the first CNN convolutional layer, and then the CNN model is fine-Trained by scene image patches with a linear classifier. The new CNN model is applied to Chinese scene text detection and is evaluated with a multilingual image dataset, which labels Chinese, English and numerals texts separately. More than 10% detection precision gain is observed over two CNN models.

Original languageEnglish
Title of host publication2015 IEEE China Summit and International Conference on Signal and Information Processing, ChinaSIP 2015 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages428-432
Number of pages5
ISBN (Electronic)9781479919482
DOIs
Publication statusPublished - 31 Aug 2015
EventIEEE China Summit and International Conference on Signal and Information Processing, ChinaSIP 2015 - Chengdu, China
Duration: 12 Jul 201515 Jul 2015

Conference

ConferenceIEEE China Summit and International Conference on Signal and Information Processing, ChinaSIP 2015
CountryChina
CityChengdu
Period12/07/1515/07/15

    Fingerprint

Keywords

  • Convolutional codes
  • Detection algorithms
  • Feature extraction
  • Machine learning
  • Neural networks
  • Training
  • Unsupervised learning

Cite this

Ren, X., Chen, K., Yang, X., Zhou, Y., He, J., & Sun, J. (2015). A new unsupervised convolutional neural network model for Chinese scene text detection. In 2015 IEEE China Summit and International Conference on Signal and Information Processing, ChinaSIP 2015 - Proceedings (pp. 428-432). [7230438] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ChinaSIP.2015.7230438