Salient views and view-dependent dictionaries for object recognition
作者：
Highlights：
• A sparse representation-based approach is proposed to determine the salient views of 3D objects.
• The salient views are categorized into boundary representative and side representative views.
• We present a sparse representation-based approach for estimating the boundary representative views.
• We determine the side representative views based on a minimum reconstruction error criterion.
• We introduce view-dependent dictionaries for applications in 3D object recognition and retrieval.
摘要
Highlights•A sparse representation-based approach is proposed to determine the salient views of 3D objects.•The salient views are categorized into boundary representative and side representative views.•We present a sparse representation-based approach for estimating the boundary representative views.•We determine the side representative views based on a minimum reconstruction error criterion.•We introduce view-dependent dictionaries for applications in 3D object recognition and retrieval.
论文关键词：Salient view,Characteristic view class,View geometry,Sparse representation,View-dependent dictionaries,Object recognition
论文评审过程：Received 23 August 2014, Revised 4 December 2014, Accepted 16 January 2015, Available online 23 January 2015, Version of Record 17 June 2015.
论文官网地址：https://doi.org/10.1016/j.patcog.2015.01.013
