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

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.

[1]  Moon S. Kim,et al.  Development of hyperspectral imaging technique for the detection of apple surface defects and contaminations , 2004 .

[2]  Rouben Rostamian,et al.  Technical Note: Algorithms for Parameterization of Dynamics of Inertia-Based Apple Orientation , 2008 .

[3]  Da-Wen Sun,et al.  Improving quality inspection of food products by computer vision: a review , 2004 .

[4]  Y. R. Chen,et al.  Multispectral detection of fecal contamination on apples based on hyperspectral imagery: Part II. Application of hyperspectral fluorescence imaging , 2002 .

[5]  M. Destain,et al.  Development of a multi-spectral vision system for the detection of defects on apples , 2005 .

[6]  Rouben Rostamian,et al.  Orientation of Apples Using Their Inertial Properties , 2008 .

[7]  James A. Throop,et al.  Influence of time, bruise-type, and severity on near-infrared reflectance from apple surfaces for automatic bruise detection , 1994 .

[8]  D. L. Peterson,et al.  Performance of a System for Apple Surface Defect Identification in Near-infrared Images , 2005 .

[9]  Moon S. Kim,et al.  Automated detection of fecal contamination of apples by multispectral laser-induced fluorescence imaging. , 2003, Applied optics.

[10]  James A. Throop,et al.  Quality evaluation of apples based on surface defects: development of an automated inspection system , 2005 .

[11]  Moon S Kim,et al.  Using parabolic mirrors for complete imaging of apple surfaces. , 2009, Bioresource technology.

[12]  Yud-Ren Chen,et al.  Detection of fecal contamination on apples with nanosecond-scale time-resolved imaging of laser-induced fluorescence. , 2005, Applied optics.

[13]  Yud-Ren Chen,et al.  Machine vision technology for agricultural applications , 2002 .

[14]  D. P. Whitelock,et al.  APPLE SHAPE AND ROLLING ORIENTATION , 2006 .

[15]  M. L. Stone,et al.  Peach Physical Characteristics for Orientation , 1996 .

[16]  Rouben Rostamian,et al.  Theoretical Analysis of Stability of Axially Symmetric Rotating Objects with Regard to Orienting Apples , 2008 .