en
Scientific article
English

Building Hierarchical Representations for Oracle Character and Sketch Recognition

Published inIEEE transactions on image processing, vol. 25, no. 1, p. 104-118
Publication date2016
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 Representation
  • Oracle Character Recognition
  • Sketch Recognition
Citation (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
Main files (1)
Article (Published version)
accessLevelRestricted
Identifiers
ISSN of the journal1057-7149
582views
1downloads

Technical informations

Creation10/07/2016 4:56:00 PM
First validation10/07/2016 4:56:00 PM
Update time03/15/2023 12:48:51 AM
Status update03/15/2023 12:48:50 AM
Last indexation01/16/2024 9:58:11 PM
All rights reserved by Archive ouverte UNIGE and the University of GenevaunigeBlack