Support vector machine-based object classification for robot arm system

Vo Duy Cong, Thai Thanh Hiep


In this paper, a support vector machine (SVM) model is trained to classify objects in the automatic sorting system using a robot arm. The robot arm is used to grab objects and move them to the right position according to their shape predicted by the SVM model. The position of objects in the image is identified by using the contouring technique. The centroid of objects is calculated from the image moment of the object's contour. The calibration is conducted to get the parameters of the camera and combine with the pinhole camera model to compute the 3D position of the objects. The feature vector for SVM training is the zone feature and the SVM kernel is the Gaussian kernel. In the experiment, the SVM model is used to classify four objects with different shapes. The results show that the accuracy of the SVM classifier is 99.72%, 99.4%, 99.4% and 99.88% for four objects, respectively.


classification; Raspberry Pi; robot arm; sorting system; support vector machine;

Full Text:



Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

International Journal of Electrical and Computer Engineering (IJECE)
p-ISSN 2088-8708, e-ISSN 2722-2578

This journal is published by the Institute of Advanced Engineering and Science (IAES) in collaboration with Intelektual Pustaka Media Utama (IPMU).