Orienting apples for imaging using their inertial properties and random apple loading

被引:26
作者
Lefcourt, A. M. [1 ,2 ]
Narayanan, P. [1 ,2 ]
Tasch, U. [2 ]
Kim, M. S. [1 ]
Reese, D. [1 ,3 ]
Rostamian, R. [4 ]
Lo, Y. M. [3 ]
机构
[1] USDA ARS, Henry A Wallace Beltsville Agr Res Ctr, Environm Microbiol & Food Safety Lab, Beltsville, MD 20705 USA
[2] Univ Maryland Baltimore Cty, Dept Mech Engn, Baltimore, MD USA
[3] Univ Maryland, Dept Nutr & Food Sci, College Pk, MD 20742 USA
[4] Univ Maryland Baltimore Cty, Dept Math & Stat, Baltimore, MD USA
关键词
LASER-INDUCED FLUORESCENCE; FECAL CONTAMINATION; SURFACE-DEFECTS; ORIENTATION; SYSTEM; INSPECTION; VISION; TIME;
D O I
10.1016/j.biosystemseng.2009.06.002
中图分类号
S2 [农业工程];
学科分类号
0828 ;
摘要
The inability to control apple orientation during imaging has hindered the development of automated systems for sorting apples for defects such as bruises and for safety issues such as faecal contamination. Recently, a potential method for orienting apples based on their inertial properties was discovered. To test this method, apples were rolled down a track consisting of two parallel rails. As angular velocity increased, apples generally moved to an orientation where the stem/calyx axis was parallel to the plane of the track and perpendicular to the direction of travel. However, theoretical analyses and experimental results have demonstrated that select initial loading conditions could prevent or impede this orientation process. In this study, the practical importance of initial loading conditions was tested using two different methods to randomly load apples onto a track. Replicate tests indicated that successful orientation at rates of about 80% for Red and Golden Delicious cultivar apples was random, and that only 5% of the apples exhibited undesirable loading condition and orientation. Results suggest that a commercially viable orientation system could be developed by recycling apples that are not oriented during imaging, and that it should be possible to improve single-pass orientation rates by addressing track compliance and loading velocity issues. Published by Elsevier Ltd on behalf of IAgrE.
引用
收藏
页码:64 / 71
页数:8
相关论文
共 19 条
[1]   Performance of a system for apple surface defect identification in near-infrared images [J].
Bennedsen, BS ;
Peterson, DL .
BIOSYSTEMS ENGINEERING, 2005, 90 (04) :419-431
[2]   Improving quality inspection of food products by computer vision - a review [J].
Brosnan, T ;
Sun, DW .
JOURNAL OF FOOD ENGINEERING, 2004, 61 (01) :3-16
[3]  
CARLSON RL, 1987, Patent No. 4706797
[4]   Machine vision technology for agricultural applications [J].
Chen, YR ;
Chao, KL ;
Kim, MS .
COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2002, 36 (2-3) :173-191
[5]  
Kim MS, 2002, T ASAE, V45, P2039
[6]   Development of a multi-spectral vision system for the detection of defects on apples [J].
Kleynen, O ;
Leemans, V ;
Destain, MF .
JOURNAL OF FOOD ENGINEERING, 2005, 69 (01) :41-49
[7]  
Lefcourt AM, 2008, APPL ENG AGRIC, V24, P123
[8]   Detection of fecal contamination on apples with nanosecond-scale time-resolved imaging of laser-induced fluorescence [J].
Lefcourt, AM ;
Kim, MS ;
Chen, YR .
APPLIED OPTICS, 2005, 44 (07) :1160-1170
[9]   Automated detection of fecal contamination of apples by multispectral laser-induced fluorescence imaging [J].
Lefcourt, AM ;
Kim, MS ;
Chen, YR .
APPLIED OPTICS, 2003, 42 (19) :3935-3943
[10]   Development of hyperspectral imaging technique for the detection of apple surface defects and contaminations [J].
Mehl, PM ;
Chen, YR ;
Kim, MS ;
Chan, DE .
JOURNAL OF FOOD ENGINEERING, 2004, 61 (01) :67-81