A Code Based Fruit Recognition Method Via Image Convertion Using Multiple Features

This research is to propose a fast and accurate object recognition method especially for fruit recognition to be used for mobile environment. Conventional techniques are based on one or more of basic features that characterize an object: color, shape, texture and intensity, causing performance limit...

Full description

Saved in:
Bibliographic Details
Published in2014 International Conference on IT Convergence and Security (ICITCS) pp. 1 - 4
Main Authors Jang-yoon Kim, Vogl, Michael, Shin-Dug Kim
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.10.2014
Subjects
Accuracy
Feature extraction
Image color analysis
Image edge detection
Shape
Online AccessGet full text
DOI10.1109/ICITCS.2014.7021706

Cover

More Information
Summary:This research is to propose a fast and accurate object recognition method especially for fruit recognition to be used for mobile environment. Conventional techniques are based on one or more of basic features that characterize an object: color, shape, texture and intensity, causing performance limitation for mobile environment. Thus, this paper presents a combined approach that transforms those basic features into their associated code fields to generate an object code that could be used as a search key for the feature database. Experimental results have been collected using a fruit database consisting of 33 different classes of fruits and 1006 fruits overall. Thus, average accuracy of more than 90% is obtained and performance increases compared to other approaches on fruit image recognition.
DOI:10.1109/ICITCS.2014.7021706