Abstract
In recent years, fluorescence hyperspectral imaging technology has received more attention in the food inspection field because of its ability to distinguish multiple chemical ingredients. However, one persistent problem associated with this technology is how to deal with the huge amount of data acquired by the hyperspectral imaging device, and hence improve the efficiency of the application system. To solve the aforementioned problem, this paper proposed using an Independent Component Analysis with k Nearest Neighbor classifier (ICA-kNN) approach to differentiate walnut shells from walnut meat. This project will meet two goals: (1) select optimal wavelengths to reduce data redundancy, and (2) classify walnut shells or meat according to selected wavelengths. First, the ICA ranking method was applied to select 4–10 optimal wavelengths based on their ability to distinguish the four walnut shell and meat categories: dark meat, light meat, inner shell and outer shell. Then, the kNN classifier was used to distinguish walnut shells from meat according to the computed optimal wavelengths. A total of 5,496 samples were studied, and an overall 90.6% detection rate was achieved given 10 optimal wavelengths, which constituted only 13% of the total acquired hyperspectral image data. In order to further evaluate the proposed method, the classification results of the ICA-kNN approach were also compared to the kNN classifier method alone. The experimental results showed that the ICA-kNN method with a few wavelengths had the same performance as the kNN classifier alone using information from all 79 wavelengths. This demonstrated the effectiveness of the proposed ICA-kNN method to classify walnut shells and meat.
Similar content being viewed by others
References
J. Jones, R. Mueller, V. Sambeek, Nut Production Handbook for Eastern Black Walnut (Southwest Missouri Resources, Convervation & Development (RC&D), Inc., 1998)
Hammons Products Company, World Consumption and Production Trends. (International Nut Council, 1998)
P. Krishnan, A. Berlage, Trans. ASAE. 27, 1990–1992 (1984)
B. Zhu, L. Jiang, Y. Tao, Opt. Eng. 46(1), 017201-1-9 (2007)
X. Cheng, Y.R. Chen, Y. Tao, C.Y. Wang, M.S. Kim, A.M. Lefcourt, Trans. ASAE. 47(4), 1313–1320 (2004)
A.M. Vargas, Y. Tao, M. Kim, A.M. Lefcourt, Y. Luo, Y.R. Chen, 2004 ASAE Annual International Meeting, Ottawa, Ontario, Canada, August 31–July 4, 2004
B. Zhu, L. Jiang, Y. Luo, Y. Tao, J. Food Eng. 81(4), 741–749 (2007)
L. Ma, Y. Tao, Trans. ASAE. 48(2), 681–690 (2005)
Y. Tao, Z. Chen, C. Griffis, IEE Proc. Vis. Image Signal Process. 151(5), 337–344 (2004)
L. Jiang, B. Zhu, X. Rao, G. Berney, Y. Tao, J. Food Eng. 81(1), 108–117 (2007)
L. Jiang, B. Zhu, X. Rao, G. Berney, Y. Tao, ASABE 2007 Annual Meeting, 2007
L. Jiang, B. Zhu, H. Jing, X. Chen, X. Rao, Y. Tao, Trans. ASABE. 50(1), 153–160 (2007)
L. Jiang, B. Zhu, X. Rao, G. Berney, Y. Tao, ASABE 2007 Annual Meeting, 2007
R. Lu, Trans. ASAE. 46(2), 523–530 (2003)
A. Vargas, M. Kim, Y. Tao, A.M. Lefcourt, Y. Luo, Y.R. Chen, J. Food Eng. 70(8–2005), 471–476 (2004)
B. Park, K.C. Lawrence, W.R. Windham, R.J. Buhr, Trans. ASAE. 45(6), 2017–2026 (2002)
R.P. Haff, T. Pearson, Trans. ASABE. 49(4), 1105–1113 (2006)
S.R. Delwiche, C.S. Gaines, Appl. Eng. Agri. 21(4), 681–688 (2005)
J. Xing, M. Ngadi, N. Wang, J.D. Baerdemaeker, Paper number 063018, 2006 ASAE Annual Meeting, 2006
Y. Peng, R. Lu, Trans. ASAE. 49(1), 269–275 (2006)
M. Kim, Y. Chen, P. Mehl, Trans. ASAE. 44(3), 721–729 (2001)
Y.R. Chen, K. Chao, M.S. Kim, Comput. Electron. Agri. 36(2–3), 173–191 (2002)
J. Herault, C. Jutten, Neural Networks for Computing (Snowbird, Utah, 1986)
P. Comon, Signal Processing 36(3), 287–314 (1994)
A. Belouchrani, K. Abed-Meraim, J.F. Cardoso, E. Moulines, IEEE Trans. Signal Process. 45(2), 434–444 (1997)
A. Ziehe, K.-R. Miller, ICANN’98, Skovde, 1998, pp. 675–680
H. Du, H. Qi, X. Wang, R. Ramanath, W.E. Snyder, 2003. in Proceedings of the 32nd Applied Imagery Pattern Recognition Workshop (AIPR ‘03), Washington, DC, USA, October 2003, pp. 93–98
O. Lyman, An Introduction to Statistical Methods and Data Analysis, 5th edn. (Michael Longnecker, 2001)
Acknowledgments
The authors gratefully acknowledge funding support from USDA/NRI (Grant # 2005-35503-16213). The authors also thank Dr. Yud-Ren Chen, Dr. Moon Kim, and Ms. Diane Chan in the USDA ISL (Beltsville, MD) for providing the hyperspectral imaging system to scan the samples. Thanks also go to Dr. Xin Chen and Dr. Hansong Jing for sharing their valuable suggestions and comments and Mr. Xiuqin Rao and Mr. Gary Seibel for helping us build the walnut conveyer and processing system.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Zhu, B., Jiang, L., Jin, F. et al. Walnut shell and meat differentiation using fluorescence hyperspectral imagery with ICA-kNN optimal wavelength selection. Sens. & Instrumen. Food Qual. 1, 123–131 (2007). https://doi.org/10.1007/s11694-007-9015-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11694-007-9015-z