TY - JOUR
T1 - Study of active learning-based trademark number recognition method
AU - Shi, Yujie
AU - Wu, Jian
AU - Sheng, Victor S.
AU - Cui, Zhiming
AU - Zhao, Pengpeng
PY - 2014/3/1
Y1 - 2014/3/1
N2 - In most image classification algorithms, the classifier model needs to train a large number of training samples. In practical application, labeling numbers of samples is a tedious and time-consuming task. So, how to select fewer suitable training samples from the numbers of unlabeled samples is a difficulty in the image classification algorithm. This paper proposes a trademark number recognition technique based on active learning algorithm. The method uses the human interaction to get trademark number area, and then uses the projection method to extract character characteristic which using the characteristic to split characters. Finally, use BvSB active learning algorithm to select high information samples which was used to train support vector machine classifier, and use the trained classifier to recognize trademark number. The experimental result shows that the classifier trained by the method has higher classification accuracy in the case of labeled fewer samples.
AB - In most image classification algorithms, the classifier model needs to train a large number of training samples. In practical application, labeling numbers of samples is a tedious and time-consuming task. So, how to select fewer suitable training samples from the numbers of unlabeled samples is a difficulty in the image classification algorithm. This paper proposes a trademark number recognition technique based on active learning algorithm. The method uses the human interaction to get trademark number area, and then uses the projection method to extract character characteristic which using the characteristic to split characters. Finally, use BvSB active learning algorithm to select high information samples which was used to train support vector machine classifier, and use the trained classifier to recognize trademark number. The experimental result shows that the classifier trained by the method has higher classification accuracy in the case of labeled fewer samples.
KW - Active learning
KW - BvSB
KW - Support Vector Machine
KW - Trademark number recognition
UR - http://www.scopus.com/inward/record.url?scp=84896994006&partnerID=8YFLogxK
U2 - 10.1260/1748-3018.8.1.71
DO - 10.1260/1748-3018.8.1.71
M3 - Article
AN - SCOPUS:84896994006
VL - 8
SP - 71
EP - 84
JO - Journal of Algorithms and Computational Technology
JF - Journal of Algorithms and Computational Technology
SN - 1748-3018
IS - 1
ER -