UNIGE document Scientific Article
previous document  unige:88089  next document
add to browser collection

Building Hierarchical Representations for Oracle Character and Sketch Recognition

Guo, Jun
Wang, Changhu
Chao, Hongyang
Rui, Yong
Published in IEEE transactions on image processing. 2016, vol. 25, no. 1, p. 104-118
Abstract In this paper, we study oracle character recognition and general sketch recognition. First, a data set of oracle characters, which are the oldest hieroglyphs in China yet remain a part of modern Chinese characters, is collected for analysis. Second, typical visual representations in shape- and sketch-related works are evaluated. We analyze the problems suffered when addressing these representations and determine several representation design criteria. Based on the analysis, we propose a novel hierarchical representation that combines a Gabor-related low-level representation and a sparse-encoder-related mid-level representation. Extensive experiments show the effectiveness of the proposed representation in both oracle character recognition and general sketch recognition. The proposed representation is also complementary to convolutional neural network (CNN)-based models. We introduce a solution to combine the proposed representation with CNN-based models, and achieve better performances over both approaches. This solution has beaten humans at recognizing general sketches.
Keywords Hierarchical RepresentationOracle Character RecognitionSketch Recognition
Full text
Article (Published version) (3.7 MB) - document accessible for UNIGE members only Limited access to UNIGE
Other version: http://ieeexplore.ieee.org/document/7327196/
Research groups Computer Vision and Multimedia Laboratory
Viper group
(ISO format)
GUO, Jun et al. Building Hierarchical Representations for Oracle Character and Sketch Recognition. In: IEEE transactions on image processing, 2016, vol. 25, n° 1, p. 104-118. doi: 10.1109/TIP.2015.2500019 https://archive-ouverte.unige.ch/unige:88089

512 hits

1 download


Deposited on : 2016-10-10

Export document
Format :
Citation style :