Mars image segmentation with most relevant features among wavelet and color features

Rashno, A, Saraee, MH ORCID: https://orcid.org/0000-0002-3283-1912 and Sadri, S 2015, Mars image segmentation with most relevant features among wavelet and color features , in: AI & Robotics (IRANOPEN), 2015, 12 April 2015.

PDF - Published Version Restricted to Repository staff only Download (401kB) | Request a copy

Abstract

Mars rover is a robot which explores the Mars surface, is equipped to front-line Panoramic Camera (Pancam). Automatic processing and segmentation of images taken by Pancam is one of the most important and most significant tasks of Mars rover since the transformation cost of images from Mars to earth is extremely high. In this paper, a new feature vector for image pixels will be proposed as well as a new feature selection schema based on ant colony optimization (ACO). Then, the most relevant features are presented for multiclass Support Vector Machine (SVM) classifier which led to high accuracy pixel classification and then image segmentation. Our proposed method is compared with genetic algorithm feature selection, experimental results show that the proposed method outperforms this method in the terms of accuracy and efficiently.

Item Type:	Conference or Workshop Item (Paper)
Schools:	Schools > School of Computing, Science and Engineering
Journal or Publication Title:	AI & Robotics (IRANOPEN), 2015
Publisher:	IEEE
Related URLs:	Publisher Publication
Funders:	Non funded research
Depositing User:	Prof. Mo Saraee
Date Deposited:	24 Oct 2016 10:00
Last Modified:	15 Feb 2022 21:20
URI:	https://usir.salford.ac.uk/id/eprint/40437

Actions (login required)

Edit record (repository staff only)