Comparative Study Of Local Descriptors For Measuring Object Tazonomy

摘要：

Many object descriptors have been proposed in the state of the art. For many reasons (occlusion, point of view, acquisition conditions...), local descriptors have a better robustness for image understanding applications. The goal of this paper is to make a comparative study of eight recent local descriptors. The objective is here to quantify their ability to generate automatically an object taxonomy. In order to answer this question, we use the Caltech256 benchmark which provides a large object taxonomy used as reference. This study shows that SIFT, differential invariants and shape context descriptors are the best ones to achieve this goal.

作者: B. Hemery H.Laurent B.Emile C. Rosenberger

作者单位: Laboratoire Greyc ENSICAEN - Universite de Caen - CNRS 6 boulevard du Marechal Juin 14000 Caen - Fra Institut Prisme ENSI de Bourges - Universite dOrleans 88 boulevard Lahitolle 18000 Bourges-France

会议类型: 国际会议

会议名称: The Fifth International Conference on Image and Graphics(第五届国际图像图形学学术会议 ICIG 2009)

会议地点: 西安

会议语种:英文

页码: 276-281

在线出版日期: 2009-09-20（万方平台首次上网日期，不代表论文的发表时间）