Comparative analysis of texture classification based on low and high order local features

被引：0

作者：

Avramovic, Aleksej ^{[1
,2
]}

Sevo, Igor ^{[2
]}

Reljin, Irini ^{[1
]}

机构：

[1] Univ Belgrade, Sch Elect Engn, Bulevar Kralja Aleksandra 73, Belgrade 11000, Serbia

[2] Univ Banja Luka, Fac Elect Engn, Banja Luka 78000, Bosnia & Herceg

来源：

2015 23RD TELECOMMUNICATIONS FORUM TELFOR (TELFOR) | 2015年

关键词：

classification; feature; texture; SIFT; CNN; SCENE;

D O I：

暂无

中图分类号：

TN [电子技术、通信技术];

学科分类号：

0809 ;

摘要：

The importance of texture for recognition of objects, scenes and events is well-known and used in various computer vision tasks. Until recently, best-performing texture classification algorithms relied on processing of low-level local features and statistical learning based adjustment of classifiers. Convolutional neural networks introduced higher order local features and improved classification results significantly. In this paper, we compared texture classification based on low-lever and high order local features. Also, we demonstrated the ability of convolutional networks to learn high order features from one dataset and to efficiently use that knowledge on a different dataset.

引用

页码：799 / 802

页数：4