Writer identification using oriented Basic Image Features and the Delta encoding
作者：
Highlights：
• We present a full description of the oBIF Column method as applied to writer identification.
• We evaluate the oBIF Column encoding scheme using the IAM dataset, producing a performance of 99% for 301 writers.
• We present the Delta encoding, an addition to the oBIF Column scheme.
• We evaluate the Delta encoding using two leading international competitions, gaining first place in both.
• We show how our method uses different sources of information.
摘要
Highlights•We present a full description of the oBIF Column method as applied to writer identification.•We evaluate the oBIF Column encoding scheme using the IAM dataset, producing a performance of 99% for 301 writers.•We present the Delta encoding, an addition to the oBIF Column scheme.•We evaluate the Delta encoding using two leading international competitions, gaining first place in both.•We show how our method uses different sources of information.
论文关键词：Writer identification,Handwriting,Texture,oBIF Columns,Delta encoding
论文评审过程：Received 30 January 2013, Revised 21 September 2013, Accepted 30 November 2013, Available online 12 December 2013.
论文官网地址：https://doi.org/10.1016/j.patcog.2013.11.029
