Human visual system inspired object detection and recognition

Author

Mandal, Debashree ; Panetta, Karen ; Agaian, Sos

Author_Institution

Dept. of Electr. & Comput. Eng., Tufts Univ., Medford, MA, USA

fYear

2012

fDate

23-24 April 2012

Firstpage

145

Lastpage

150

Abstract

This paper presents a new generic framework for human visual system inspired object detection and recognition and introduces the idea of feature extraction based on the human visual sensitivity. These methods can greatly enhance robotic vision applications. Additionally a new computationally effective object detection algorithm is presented based on image morphology and visual sensitivity. This new method surpasses the performance of the existing method based on traditional edge detectors. We also present the effectiveness of the algorithm on under-illuminated images.

Keywords

feature extraction; object detection; object recognition; robot vision; computer vision techniques; feature extraction; generic framework; human visual sensitivity; human visual system inspired object detection; human visual system inspired object recognition; image morphology; robotic vision applications; Feature extraction; Humans; Image edge detection; Object detection; Training; Visual systems; Visualization; Feature Extraction; Human Visual System; Image Morphology; Object Detection; Robot Vision;

fLanguage

English

Publisher

ieee

Conference_Titel

Technologies for Practical Robot Applications (TePRA), 2012 IEEE International Conference on

Conference_Location

Woburn, MA

Print_ISBN

978-1-4673-0855-7

Type

conf

DOI

10.1109/TePRA.2012.6215669

Filename

6215669