Query-expanded collaborative representation based classification with class-specific prototypes for object recognition
作者：
Highlights：
• We propose a novel LinearRC for object recognition with less constraints.
• We expand the single query image into a query set for robust representation.
• We learn the class-specific prototypes by maximizing canonical correlation.
• A multivariate CRC using minimal normalized residual is to identify the query.
• We validate the effectiveness of our method with extensive experiments.
摘要
Highlights•We propose a novel LinearRC for object recognition with less constraints.•We expand the single query image into a query set for robust representation.•We learn the class-specific prototypes by maximizing canonical correlation.•A multivariate CRC using minimal normalized residual is to identify the query.•We validate the effectiveness of our method with extensive experiments.
论文关键词：Object recognition,Linear representation based classifier,Collaborative representation based classification,Prototype generation,Query expansion
论文评审过程：Received 3 July 2013, Revised 25 April 2014, Accepted 14 May 2014, Available online 28 May 2014.
论文官网地址：https://doi.org/10.1016/j.patcog.2014.05.011
