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

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, - Proceedings
Place of PublicationPiscataway, NJ (US)
PublisherIEEE
Pages428-432
Number of pages5
ISBN (Print)978-1-4799-1948-2
DOIs
Publication statusPublished - 2015
Event2015 IEEE China summit and international conference on Signal and Information Processing - Chengdu, China
Duration: 12 Jul 201515 Jul 2015

Conference

Conference2015 IEEE China summit and international conference on Signal and Information Processing
Abbreviated titleChinaSIP 2015
CountryChina
CityChengdu
Period12/07/1515/07/15

Keywords

  • convolutional codes
  • detection algorithms
  • feature extraction
  • machine learning
  • neural networks
  • training
  • unsupervised learning

Fingerprint Dive into the research topics of 'A new unsupervised convolutional neural network model for Chinese scene text detection'. Together they form a unique fingerprint.

  • 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, - Proceedings (pp. 428-432). IEEE. https://doi.org/10.1109/ChinaSIP.2015.7230438