Automatic Produce Grading System
The development of a machine vision system for automated high-speed produce grading is described. Image processing techniques were used to obtain an estimate of the volume of each item, which was then related to the weight through a closed-loop calibration. Accurate weight estimation led to more accurate and better control over the spread of package weights. This reduced the average package weight by approximately 20%, with a standard deviation of 2.5 g for a nominal 100 g package. Improved processing efficiencies doubled the throughput and significantly increased the profitability of the packinghouse.
KeywordsSpecular Reflection Machine Vision System Central View Target Weight Image Processing Operation
A large project such as this is never a one-man effort. My role in the project related to the image and signal processing aspects. The other members of the development team were: Ralph Ball and Harvey Barraclough, who focussed on the mechanical engineering aspects of the project; Ken Mercer, who developed the intelligent actuators; Colin Plaw, who developed the LabVIEW based control system; Andrew Gilman, who investigated high-speed weighing using load cells; and Geoff Lewis from the packinghouse, who provided the test system and copious quantities of asparagus for testing.
We also acknowledge funding for this project from Technology New Zealand through a Technology for Business Growth Grant.
- 1.Bailey DG (2003) Sub-pixel estimation of local extrema. In: Image and Vision Computing New Zealand (IVCNZ’03), Palmerston North, New Zealand, 26–28 November, 2003, pp 414–419Google Scholar
- 3.Bailey DG, Mercer KA, Plaw C, Ball R, Barraclough H (2004) High speed weight estimation by image analysis. In: 2004 New Zealand National Conference on Non Destructive Testing, Palmerston North, New Zealand, 27–29 July, 2004, pp 89–96Google Scholar
- 4.Bailey DG, Mercer KA, Plaw C, Ball R, Barraclough H (2001) Three dimensional vision for real-time produce grading. In: Machine Vision and Three-Dimensional Imaging Systems for Inspection and Metrology II, Boston, Massachusetts, USA, vol SPIE 4567, 29–30 October, 2001, pp 171–178, doi: 10.1117/12.455254Google Scholar
- 6.Davies ER (2005) Machine vision: theory, algorithms, practicalities, 3rd edn. Morgan Kaufmann, San FranciscoGoogle Scholar
- 7.Gilman A, Bailey DG (2005) High speed weighing using impact on load cells. In: IEEE Region 10 Conference (IEEE Tencon’05), Melbourne, Australia, 21–24 November, 2005, doi: 10.1109/TENCON. 2005.301118Google Scholar
- 8.Gilman A, Bailey DG (2002) Using the impact on load cells for high-speed weighing. In: Ninth Electronics New Zealand Conference (ENZCon’02), Dunedin, New Zealand, 14–15 November, 2002, pp 12–17Google Scholar
- 9.Gonzalez RC, Woods RE (2008) Digital image processing, 3rd edn. Prentice-Hall, New JerseyGoogle Scholar
- 10.Mercer K, Bailey DG, Plaw C, Ball R, Barraclough H (2002) Intelligent actuators for a high speed grading system. In: Ninth Electronics New Zealand Conference (ENZCon’02), Dunedin, New Zealand, 14–15 November, 2002, pp 61–65Google Scholar
- 11.Morales-Blancas EF, Cárcamo RC, Cisneros-Zevallos L (2001) Determination of shape parameters for asparagus spears by 3-D digitizing. In: 2001 Institute of Food Technologists Annual Meeting, New Orleans, Louisianna, 23–27 June, 2001, paper 88C–32Google Scholar
- 12.Rigney MP, Brusewitz GH (1992) Asparagus shape features for quality assessment. Trans Am Soc Agric Eng 35(5):1607–1613Google Scholar
- 13.Rigney MP, Brusewitz GH, Kranzler GA (1992) Asparagus defect inspection with machine vision. Trans Am Soc Agric Eng 35(6):1873–1878Google Scholar