By Topic

Exterior quality inspection of rice based on computer vision

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
Mingyin Yao ; Coll. of Eng., Jiangxi Agric. Univ., Nanchang, China ; Muhua Liu ; Huadong Zheng

To develop an online inspection system of rice exterior quality (head rice rate, chalk rice, crackle rice) based on computer vision. The system was developed after analyzing the optic characteristics of rice kernel in the platform of VC + + 6.0 software. The five varieties of rice kernel Jinyou974, Gangyou182, Zhongyou205, Jiahe212, and Changnonggeng-2 were selected as experimental samples. The methods, such as gray transformation, automatic threshold segmentation, area labeling, were applied to extract single rice kernel image from collected mass rice kernel images. The chalk rice and crackle rice were inspected by the above methods. To inspect the head rice rate, the ten characteristic parameters, such as the area and perimeter of rice kernel, were selected as the inspection characteristic of head rice, and the method of principal component analysis was carried out to process substantive data. The optimal threshold of distinguishing head rice was made sure. The results showed that the accurate ratio of detecting crackle rice was 96.41%, the correct ratio of detecting chalk rice was 94.79%, and the accurate ratio of detecting head rice was 96.20%. The analysis indicated efficient discrimination from different rice exterior quality by computer vision.

Published in:

World Automation Congress (WAC), 2010

Date of Conference:

19-23 Sept. 2010