PSI: Patch-based script identification using non-negative matrix factorization

作者：

Highlights：

• A novel method for script identification of ancient manuscript is proposed.

• Image patches are selected and extracted as lowest level of information. This level of information allows for robust representation against noise and at the same time captures local properties of objects.

• Non-Negative Matrix factorization is used for learning of features that perform better than hand designed features.

• The proposed method is versatile and can be applied on different level of layouts.

摘要

•A novel method for script identification of ancient manuscript is proposed.•Image patches are selected and extracted as lowest level of information. This level of information allows for robust representation against noise and at the same time captures local properties of objects.•Non-Negative Matrix factorization is used for learning of features that perform better than hand designed features.•The proposed method is versatile and can be applied on different level of layouts.

论文关键词：Script identification,Non-negative matrix factorization,Patch representation,Clustering

论文评审过程：Received 2 May 2016, Revised 14 February 2017, Accepted 15 February 2017, Available online 21 February 2017, Version of Record 2 March 2017.

论文官网地址：https://doi.org/10.1016/j.patcog.2017.02.020