Ripe Tomato Recognition with Computer Vision

DOI

10.2991/iiicec-15.2015.107How to use a DOI?

Keywords

Computer Vision; Ripe Tomato Recognition; Image Segmentation; Canny Operator

Abstract

In order to realize the tomato harvest machinery automation, this paper presents a method for automatic recognition of ripe tomato with computer vision. First, the H color component in HSI color space is exploited as the color feature parameter for identification. The RGB tomato image acquired by computer vision is transformed into HIS image, we cut off ripe tomato region based on the gray distribution of H component using the threshold method. Then, Canny operator is used to edge detection, after corrosion expansion, the tomato centroid coordinates would be marked. Experiments proceed with the image taken by a CCD camera of tomato in different lighting conditions. The results show that, our algorithm can identify ripe tomato under natural light fast and ripe tomatoes in fields can be separated from each other with a very good recognition effect.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Fang Zhang
PY  - 2015/03
DA  - 2015/03
TI  - Ripe Tomato Recognition with Computer Vision
BT  - Proceedings of the 2015 International Industrial Informatics and Computer Engineering Conference
PB  - Atlantis Press
SP  - 466
EP  - 469
SN  - 2352-538X
UR  - https://doi.org/10.2991/iiicec-15.2015.107
DO  - 10.2991/iiicec-15.2015.107
ID  - Zhang2015/03
ER  -