Chapter

Computer Analysis of Images and Patterns

Volume 9257 of the series Lecture Notes in Computer Science pp 518-528

Date:

3D Texture Recognition for RGB-D Images

  • Guoqiang ZhongAffiliated withDepartment of Computer Science and Technology, Ocean University of China
  • , Xin MaoAffiliated withDepartment of Computer Science and Technology, Ocean University of China
  • , Yaxin ShiAffiliated withDepartment of Computer Science and Technology, Ocean University of China
  • , Junyu DongAffiliated withDepartment of Computer Science and Technology, Ocean University of China Email author 

* Final gross prices may vary according to local VAT.

Get Access

Abstract

In this paper, we present a novel 3D object recognition system. In this system, we capture both the color and depth information of 3D objects using Kinect, and represent them in RGB-D images. To alleviate the deformations and partial defects of the obtained 3D surface textures, 3D texture reconstruction techniques are applied. In order to improve the recognition accuracy, we exploit metric learning methods for the K-nearest neighbor (KNN) classifier. Promising results are obtained on a real-world 3D object recognition application.

Keywords

3D object recognition RGB-D images 3D texture recognition 3D texture reconstruction Metric learning