Pattern field classification with style normalized transformation

Authors:
Xu-Yao Zhang;Kaizhu Huang;Cheng-Lin Liu
Affiliations:
National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China;National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China;National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China
Venue:
IJCAI'11 Proceedings of the Twenty-Second international joint conference on Artificial Intelligence - Volume Volume Two
Year:
2011

Citing 9
Cited 0

Modified Quadratic Discriminant Functions and the Application to Chinese Character Recognition

IEEE Transactions on Pattern Analysis and Machine Intelligence
Discriminant Adaptive Nearest Neighbor Classification

IEEE Transactions on Pattern Analysis and Machine Intelligence
Multitask Learning

Machine Learning - Special issue on inductive transfer
Style Context with Second-Order Statistics

IEEE Transactions on Pattern Analysis and Machine Intelligence
Style Consistent Classification of Isogenous Patterns

IEEE Transactions on Pattern Analysis and Machine Intelligence
Separating Style and Content with Bilinear Models

Neural Computation
Analytical Results on Style-Constrained Bayesian Classification of Pattern Fields

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Survey on Transfer Learning

IEEE Transactions on Knowledge and Data Engineering
CASIA Online and Offline Chinese Handwriting Databases

ICDAR '11 Proceedings of the 2011 International Conference on Document Analysis and Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

Field classification is an extension of the traditional classification framework, by breaking the i.i.d. assumption. In field classification, patterns occur as groups (fields) of homogeneous styles. By utilizing style consistency, classifying groups of patterns is often more accurate than classifying single patterns. In this paper, we extend the Bayes decision theory, and develop the Field Bayesian Model (FBM) to deal with field classification. Specifically, we propose to learn a Style Normalized Transformation (SNT) for each field. Via the SNTs, the data of different fields are transformed to a uniform style space (i.i.d. space). The proposed model is a general and systematic framework, under which many probabilistic models can be easily extended for field classification. To transfer the model to unseen styles, we propose a transductive model called Transfer Bayesian Rule (TBR) based on self-training. We conducted extensive experiments on face, speech and a large-scale handwriting dataset, and got significant error rate reduction compared to the state-of-the-art methods.