A New Object Recognition Approach Using Combination of Texture, Color and Shape Features

Kadir, Abdul and Azha, Khairul and Irianto, Irianto (2014) A New Object Recognition Approach Using Combination of Texture, Color and Shape Features. In: iDECON 2014, 22-23 September 2014, Avilion Legacy Hotel, Melaka. (In Press)

PDF idecon2014_submission_20.pdf - Accepted Version Restricted to Registered users only Download (717kB)

Abstract

This paper reports a new approach for recognizing objects by using combination of texture, color and shape features. Texture features were generated by applying statistical calculation on the image histogram. Color features were computed by using mean, standard deviation, skewness and kurtosis. Shape features were generated using combination of Shen features and basic shapes such as eccentricity and dispersion. The total features were used much less compared to approaches that involve orthogonal moments such as Krawtchouk moments, Zernike moments, or Tchebichef moments. Testing was done by using a dataset that contains 53 kinds of objects. All objects contained in the dataset were various things that can be found in supermarkets or produced by manufacturing. The result shows that the system gave 98.11% of accuracy rate.

Item Type:	Conference or Workshop Item (Paper)
Subjects:	T Technology > T Technology (General)
Divisions:	Faculty of Engineering Technology > Department of Electronics & Computer Engineering Technology
Depositing User:	Dr. Abdul Kadir
Date Deposited:	24 Nov 2014 18:14
Last Modified:	28 May 2015 04:33
URI:	http://eprints.utem.edu.my/id/eprint/13639
Statistic Details:	View Download Statistic

Actions (login required)

View Item