A weakly supervised large margin domain adaptation method for isolated handwritten digit recognition

• A domain adaptation method is proposed named as Large Margin Domain Adaptation (LMDA).
• LMDA selects a subset of data from source domain to match the target data distribution.
• LMDA jointly learns a transformation and adapts the classifier parameters.
• We extend an ensemble projection feature learning as a front end for LMDA.
• Experiments demonstrate the effectiveness of LMDA in character recognition.

Learning handwriting categories fail to perform well when trained and tested on data from different databases. In this paper, we propose a novel large margin domain adaptation algorithm which is able to learn a transformation between training and test datasets in addition to adapting the parameters of classifier using a few or even no training labeled samples from target handwriting dataset. Additionally, we developed a framework of ensemble projection feature learning for datasets representation as a front end for our algorithm to utilize the abundant unlabeled samples in target domain. Experiments on different handwritten digit datasets adaptations demonstrate that the proposed large margin domain adaptation algorithm achieves superior classification accuracy comparing with the state of the art methods. Quantitative evaluation of the proposed algorithm shows that semi-supervised adaptation utilizing one sample per class of target domain set reduces the error rates by 64.72% comparing with a corresponding SVM classifier.