Journal of Biosystems Engineering

Korean Society for Agricultural Machinery (한국농업기계학회)
권호 표지
DOI QR코드

DOI QR Code

A Simple Multispectral Imaging Algorithm for Detection of Defects on Red Delicious Apples

  • Lee, Hoyoung (Environmental Microbial and Food Safety Laboratory, Beltsville Agricultural Research Center, Agricultural Research Service, United States Department of Agriculture) ;
  • Yang, Chun-Chieh (Environmental Microbial and Food Safety Laboratory, Beltsville Agricultural Research Center, Agricultural Research Service, United States Department of Agriculture) ;
  • Kim, Moon S. (Environmental Microbial and Food Safety Laboratory, Beltsville Agricultural Research Center, Agricultural Research Service, United States Department of Agriculture) ;
  • Lim, Jongguk (National Academy of Agricultural Science, Rural Development Administration) ;
  • Cho, Byoung-Kwan (Department of Biosystems Machinery Engineering, Chungnam National University) ;
  • Lefcourt, Alan (Environmental Microbial and Food Safety Laboratory, Beltsville Agricultural Research Center, Agricultural Research Service, United States Department of Agriculture) ;
  • Chao, Kuanglin (Environmental Microbial and Food Safety Laboratory, Beltsville Agricultural Research Center, Agricultural Research Service, United States Department of Agriculture) ;
  • Everard, Colm D. (School of Biosystems Engineering, University College Dublin)
  • Received : 2014.04.25
  • Accepted : 2014.06.01
  • Published : 2014.06.01
Download PDF
⟨ Previous Next ⟩

Abstract

Purpose: A multispectral algorithm for detection and differentiation of defective (defects on apple skin) and normal Red Delicious apples was developed from analysis of a series of hyperspectral line-scan images. Methods: A fast line-scan hyperspectral imaging system mounted on a conventional apple sorting machine was used to capture hyperspectral images of apples moving approximately 4 apples per second on a conveyor belt. The detection algorithm included an apple segmentation method and a threshold function, and was developed using three wavebands at 676 nm, 714 nm and 779 nm. The algorithm was executed on line-by-line image analysis, simulating online real-time line-scan imaging inspection during fruit processing. Results: The rapid multispectral algorithm detected over 95% of defective apples and 91% of normal apples investigated. Conclusions: The multispectral defect detection algorithm can potentially be used in commercial apple processing lines.

Keywords

References

  1. Bhatt, A. K., Pant, D and R. Singh. 2012. An analysis of the performance of artificial neural network techniques for apple classification: Open Forum, May 2012: AI & Society.
  2. FDA. 2006. Questions & Answers: Taco Bell E. 2006. E. coli O157:H7 lettuce outbreak. Washington, DC.: Food and Drug Administration.
  3. FDA. 2001. Hazard analysis and critical control point (HAACP); procedures for the safe and sanitary processing and importing of juices. Washington, DC.: Food and Drug Administration.
  4. Garrido-Novell, C., Perez-Marin, D., Amigo, J. M., Fernandez-Novales, J., Guerrero, J. E and A. Garrido-Varo. 2012. Grading and color evolution of apples using RGB and hyperspectral imaging vision cameras. Journal of Food Engineering 113(2):281-288. https://doi.org/10.1016/j.jfoodeng.2012.05.038
  5. Kim, M. S., Chen, Y. R and P. M. Mehl. 2001. Hyperspectral reflectance and fluorescence imaging system for food quality and safety. Trans. ASAE 44(3):721-729.
  6. Kim, M. S., Lefcourt, A. M., Chao, K., Chen, Y. R and I. Kim. 2002. Multispectral detection of fecal contamination on apples based on hyperspectral imagery-Part I: Application of visible-Near Infrared reflectance imaging. Trans. ASAE 45(6):2027-2037.
  7. Kim, M. S., Chen, Y. R., Cho, B., Lefcourt, A. M., Chao, K and C. C. Yang. 2007. Hyperspectral reflectance and fluorescence line-scan imaging for online quality and safety inspection of apples. Sensing and Instrumentation for Food Quality and Safety 1(3):151-159. https://doi.org/10.1007/s11694-007-9017-x
  8. Kim, M. S., Lee, K., Chao, K., Lefcourt, A. M., Jun, W. and D. E. Chan. 2008. Multispectral line-scan imaging system for simultaneous fluorescence and reflectance measurements of apples. Sensing and Instrumentation for Food Quality and Safety 2(2):123-129. https://doi.org/10.1007/s11694-008-9045-1
  9. Mehl, P. M., Chao, K., Kim, M. S and Y. R. Chen. 2002. Detection of contamination on selected apple cultivars using hyperspectral and multispectral image analysis. Appl. Eng. of Agri. 18(2):219-226.
  10. Slattery, E., Livingston, M., Greene, C and K. Klonsky. 2011. Characteristics of conventional and organic apple production in the United States. Report FTS-347-01. Washington, DC.: Economic Research Service, United States Department of Agriculture.
  11. Srivastava, D. K. 2012. Efficient fruit defect detection and Glare removal algorithm by anisotropic diffusion and 2D Gabor filter. International Journal of Engineering Science & Advanced Technology 2(2):352-357.
  12. Unay, D., Gosselin, B., Kleynen, O., Leemans, V., Destain, M. F and O. Debeir. 2011. Automatic grading of bi-colored apples by multispectral machine vision. Computers and Electronics in Agriculture 75(1):204-212. https://doi.org/10.1016/j.compag.2010.11.006
  13. USDA. 2005. U.S. Fruit and Vegetable Availability and Handling Charts. Washington, DC.: United States Department of Agriculture.
  14. USDA. 2002. United States Standards for Grades of Apples. Washington, DC.: United States Department of Agriculture.
  15. Yang, C. C., Kim, M. S., Kang, S., Cho, B. K., Chao, K., Lefcourt, A. M and D. E. Chan. 2012. Red to far-red multispectral fluorescence image fusion for detection of fecal contamination on apples. Journal of Food Engineering 108(2):312-319. https://doi.org/10.1016/j.jfoodeng.2011.08.008

Cited by

  1. Differentiation of Beef and Fish Meals in Animal Feeds Using Chemometric Analytic Models vol.40, pp.2, 2015, https://doi.org/10.5307/JBE.2015.40.2.153
  2. Development of a Portable 3CCD Camera System for Multispectral Imaging of Biological Samples vol.14, pp.12, 2014, https://doi.org/10.3390/s141120262
  3. Multispectral Wavelength Selection to Detect 'Fuji' Apple Surface Defects with Pixel-sampling Analysis vol.39, pp.3, 2014, https://doi.org/10.5307/JBE.2014.39.3.166
  4. Spatial assessment of soluble solid contents on apple slices using hyperspectral imaging vol.159, 2017, https://doi.org/10.1016/j.biosystemseng.2017.03.015
  5. Near-infrared hyperspectral imaging system coupled with multivariate methods to predict viability and vigor in muskmelon seeds vol.229, 2016, https://doi.org/10.1016/j.snb.2016.02.015
  6. Discrimination methods for biological contaminants in fresh-cut lettuce based on VNIR and NIR hyperspectral imaging vol.85, 2017, https://doi.org/10.1016/j.infrared.2017.05.003
  7. On-line fresh-cut lettuce quality measurement system using hyperspectral imaging vol.156, 2017, https://doi.org/10.1016/j.biosystemseng.2017.01.005
  8. Detection of Lettuce Discoloration Using Hyperspectral Reflectance Imaging vol.15, pp.12, 2015, https://doi.org/10.3390/s151129511