Virtual object for evaluating adaptable K-nearest neighbor method solving various conditions of object recognition

Wittayathawon Kanlaya, Le Dung, Makoto Mizukawa

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

In order for robots to be able to manipulate the proper objects, robots firstly need visual ability to precisely recognize and identify objects. One of the most basic problems with robot vision is that environments can change under various weather conditions (various illuminations). Furthermore, each object's category consists of many objects with various poses. In order to obtain the best performance in term of accuracy and efficiency, we compared three feature extraction approaches that have been widely used to solve this problem: Principal Components Analysis (PCA), Linear Discriminant Analysis (LDA), and contour matching with Log Polar Histogram (LPH). We also introduced an improved algorithm called Adaptable K-Nearest Neighbor (AK-NN) that allows the object recognition system to use an automatic adaptable K value to improve the accuracy of classification. To evaluate the object recognition system, we generated virtual objects with various conditions for realistic testing.

Original languageEnglish
Title of host publicationICCAS-SICE 2009 - ICROS-SICE International Joint Conference 2009, Proceedings
Pages4338-4342
Number of pages5
Publication statusPublished - 2009 Dec 1
EventICROS-SICE International Joint Conference 2009, ICCAS-SICE 2009 - Fukuoka, Japan
Duration: 2009 Aug 182009 Aug 21

Publication series

NameICCAS-SICE 2009 - ICROS-SICE International Joint Conference 2009, Proceedings

Conference

ConferenceICROS-SICE International Joint Conference 2009, ICCAS-SICE 2009
CountryJapan
CityFukuoka
Period09/8/1809/8/21

Keywords

  • Object recognition
  • Robot vision
  • Virtual object

ASJC Scopus subject areas

  • Information Systems
  • Control and Systems Engineering
  • Industrial and Manufacturing Engineering

Fingerprint Dive into the research topics of 'Virtual object for evaluating adaptable K-nearest neighbor method solving various conditions of object recognition'. Together they form a unique fingerprint.

  • Cite this

    Kanlaya, W., Dung, L., & Mizukawa, M. (2009). Virtual object for evaluating adaptable K-nearest neighbor method solving various conditions of object recognition. In ICCAS-SICE 2009 - ICROS-SICE International Joint Conference 2009, Proceedings (pp. 4338-4342). [5332838] (ICCAS-SICE 2009 - ICROS-SICE International Joint Conference 2009, Proceedings).