Share Email Print

Journal of Electronic Imaging

Detecting text in natural scene images with conditional clustering and convolution neural network
Author(s): Anna Zhu; Guoyou Wang; Yangbo Dong; Brian Kenji Iwana
Format Member Price Non-Member Price
PDF $20.00 $25.00

Paper Abstract

We present a robust method of detecting text in natural scenes. The work consists of four parts. First, automatically partition the images into different layers based on conditional clustering. The clustering operates in two sequential ways. One has a constrained clustering center and conditional determined cluster numbers, which generate small-size subregions. The other has fixed cluster numbers, which generate full-size subregions. After the clustering, we obtain a bunch of connected components (CCs) in each subregion. In the second step, the convolutional neural network (CNN) is used to classify those CCs to character components or noncharacter ones. The output score of the CNN can be transferred to the postprobability of characters. Then we group the candidate characters into text strings based on the probability and location. Finally, we use a verification step. We choose a multichannel strategy to evaluate the performance on the public datasets: ICDAR2011 and ICDAR2013. The experimental results demonstrate that our algorithm achieves a superior performance compared with the state-of-the-art text detection algorithms.

Paper Details

Date Published: 29 September 2015
PDF: 10 pages
J. Electron. Imag. 24(5) 053019 doi: 10.1117/1.JEI.24.5.053019
Published in: Journal of Electronic Imaging Volume 24, Issue 5
Show Author Affiliations
Anna Zhu, Huazhong Univ. of Science and Technology (China)
Guoyou Wang, Huazhong Univ. of Science and Technology (China)
Yangbo Dong, Huazhong Univ. of Science and Technology (China)
Brian Kenji Iwana, Kyushu Univ. (Japan)

© SPIE. Terms of Use
Back to Top