Car segmentation and colour recognition

Author

Wieclawek, Wojciech ; Pietka, Ewa

Author_Institution

Dept. of Inf. & Med. Equip., Silesian Univ. of Technol., Zabrze, Poland

fYear

2014

fDate

19-21 June 2014

Firstpage

426

Lastpage

429

Abstract

The main goal of this work is to develop an algorithm to recognize the colour of a car. The methodology has been divided into three stages: car segmentation, region of interest (ROI) detection and colour recognition procedure. Proposed methodology is based on mathematical morphology operations and fuzzy systems. The computer application with graphical user interface has been implemented in MATLAB environment. Developed performance has been tested based on set of images (more than two thousand) obtained from the vehicle detection system.

Keywords

automobiles; fuzzy set theory; graphical user interfaces; image colour analysis; image recognition; image segmentation; mathematical morphology; mathematical operators; mathematics computing; traffic engineering computing; GUI; MATLAB environment; ROI detection; car segmentation; colour recognition procedure; computer application; fuzzy systems; graphical user interface; mathematical morphology operations; region of interest detection; vehicle detection system; Histograms; Image color analysis; Image segmentation; Indexing; Kernel; Support vector machines; Vehicles; HSV; car; car brand; colour recognition; detection; fuzzy system; segmentation;

fLanguage

English

Publisher

ieee

Conference_Titel

Mixed Design of Integrated Circuits & Systems (MIXDES), 2014 Proceedings of the 21st International Conference

Conference_Location

Lublin

Print_ISBN

978-83-63578-03-9

Type

conf

DOI

10.1109/MIXDES.2014.6872234

Filename

6872234