Compact MQDF classifiers using sparse coding for handwritten Chinese character recognition
作者：
Highlights：
• We use sparse coding to compact the parameters of MQDF classifier.
• An analysis is given to indicate that using the sparse representation to build compact MQDF classifier is feasible and valid.
• We learn multiple dictionaries rather than single dictionary to reduce the computational complexity.
• A weight-based assignment strategy is proposed to further alleviate the degradation of recognition accuracy.
• Experiments demonstrate the validation of the proposed methods.
摘要
•We use sparse coding to compact the parameters of MQDF classifier.•An analysis is given to indicate that using the sparse representation to build compact MQDF classifier is feasible and valid.•We learn multiple dictionaries rather than single dictionary to reduce the computational complexity.•A weight-based assignment strategy is proposed to further alleviate the degradation of recognition accuracy.•Experiments demonstrate the validation of the proposed methods.
论文关键词：Sparse coding,Compact MQDF classifier,Multiple dictionary learning,Handwritten Chinese character recognition
论文评审过程：Received 18 July 2016, Revised 1 June 2017, Accepted 30 September 2017, Available online 10 October 2017, Version of Record 8 January 2018.
论文官网地址：https://doi.org/10.1016/j.patcog.2017.09.044
