Citrus black spot detection using hyperspectral imaging
Keywords:
citrus black spot, hyperspectral imaging, spectral angle mapper, spectral information divergence, imaging processingAbstract
Abstract: This paper describes the development of a hyperspectral imaging approach for identifying fruits infected with citrus black spot (CBS). Hyperspectral images were taken of healthy fruit and those with CBS symptoms or other potentially confounding peel conditions such as greasy spot, wind scar, or melanose. Spectral angle mapper (SAM) and spectral information divergence (SID) hyperspectral analysis approaches were used to classify fruit samples into two classes: CBS or non-CBS. The classification accuracy for CBS with SAM approach was 97.90%, and 97.14% with SID. The combination of hyperspectral images and two classification approaches (SID and SAM) have proven to be effective in recognizing CBS in the presence of other potentially confounding fruit peel conditions. The study result can be a reference for the non-destructive detection of fruits infected with citrus black spot. Keywords: citrus black spot, hyperspectral imaging, spectral angle mapper, spectral information divergence, imaging processing DOI: 10.3965/j.ijabe.20140706.004 Citation: Kim D, Burks T F, Ritenour M A, Qin J W. Citrus black spot detection using hyperspectral imaging. Int J Agric & Biol Eng, 2014; 7(6): 20-27.References
[1] Chung K R, Peres N A, Timmer L W. Citrus disease exotic to Florida: Black spot, Available from: http://http://edis.ifas. ufl.edu. Accessed on [2011-03-01,]
[2] Dewdney M M. 2010. Citrus black spot. Citrus Ind. 2010; 91: 19–20.
[3] Dewdney M M, Yates J D, Ritenour M A. Identification of early citrus black spot symptoms (Identificacíon de los SíntomasIniciales de la Mancha Negra de los Cítricos). Available from: http://edis.ifas.ufl.edu/pp285. Accessed on [2011-07-01].
[4] Jimenez A R, Ceres R, Pons J L. A survey of computer vision methods for locating fruit on trees. Transactions of the. ASABE. 2010; 43: 1911–1920.
[5] Requnathan M, Lee W S. Citrus fruit identification and size determination using machine vision and ultrasonic sensors. paper no. 053017. In: ASAE Annual International Meeting. 17 July, Tampa Convention Center, Tampa, Florida, USA. American Society of Agricultural Engineers, Tampa, USA, 2005.
[6] Burks T F, Shearer S A, Payne F A. Classification of weed species using color texture features and discriminant analysis. Transactions of the ASAE, 2000; 43: 441–448.
[7] Tang L, Tian L F, Steward B L. Classification of broadleaf and grass weeds and an artificial neural network. Transactions of the ASAE, 2003; 46: 1247–1254.
[8] Pydipati R, Bu Tang rks T F, Lee W S. Identification of citrus dis¬ease using color texture features and discriminant analysis. Comput. Electron. Agr., 2006; 52: 49–59.
[9] Du C J, Sun D W. Correlating image texture features ex-tracted by five different methods with the tenderness of cooked pork ham: a feasibility study. Transactions of the ASAE, 2006; 49: 441–448.
[10] Sun D W. Hyperspectral imaging for food quality analysis and control. Academic Press, Elsevier, San Diego, USA, 2006.
[11] Jiang L, Zhu B, Rao X, Berney G, Tao Y. Discrimination of black walnut shell and pulp in hyper spectral fluorescence imagery using Gaussian kernel function approach. J. Food Eng., 2007; 81: 108–117.
[12] Zhang Y, He X J, Han J H. Texture feature-based image classification using wavelet package transform. Advances in Intelligent Computing, 2005; 3644: 165–173.
[13] Kim M S, Chen Y R, Mehl P M. Hyperspectral reflectance and fluorescence imaging system for food quality and safety. Transactions of the ASAE, 2001; 44: 721–729.
[14] Lee K J, Kang S, Kim M S, Noh S H. Hyper-spectral imaging for detection defect on apple. paper no. 053075. In: ASAE Annual International Meeting. 17 July, Tampa Convention Center, Tampa, Florida, USA. American Society of Agricultural Engineers, Tampa, USA, 2005.
[15] Park B, Windham W R, Lawrence K C, Smith D P. Con-taminant classification of poultry hyperspectral imagery using a spectral angle mapper algorithm. Biosyst. Eng., 2007; 96: 323–333.
[16] Qin J, Burks T F, Ritenour M A, Bonn W G. Detection of citrus canker using hyperspectral reflectance imaging with spectral information divergence. J. Food Eng., 2009; 93: 183–191.
[17] Yang C, Everitt J H, Bradford J M. Yield estimation from hyperspectral imagery using spectral angle mapper (SAM). Transactions of the ASABE, 2008; 51: 729–737.
[18] Shippert P. Introduction to hyperspectral image analysis. Available from http://spacejournal.ohio.edu/pdf/shippert.pdf. Accessed on [2011-07-15].
[19] Du Y, Chang C I, Ren H, Chang C C, Jensen J O. New hyperspectral discrimination measure for spectral characterization. Opt. Eng., 2004; 43: 1777–1788.
[20] Chang C I. Spectral information divergence for hyperspectral image analysis. In: International Geoscience and Remote Sensing Symposium. 28 June, Congress Center, Hamburg, Germany. IEEE Publications, Hamburg, Germany, 1999; pp. 509–511.
[2] Dewdney M M. 2010. Citrus black spot. Citrus Ind. 2010; 91: 19–20.
[3] Dewdney M M, Yates J D, Ritenour M A. Identification of early citrus black spot symptoms (Identificacíon de los SíntomasIniciales de la Mancha Negra de los Cítricos). Available from: http://edis.ifas.ufl.edu/pp285. Accessed on [2011-07-01].
[4] Jimenez A R, Ceres R, Pons J L. A survey of computer vision methods for locating fruit on trees. Transactions of the. ASABE. 2010; 43: 1911–1920.
[5] Requnathan M, Lee W S. Citrus fruit identification and size determination using machine vision and ultrasonic sensors. paper no. 053017. In: ASAE Annual International Meeting. 17 July, Tampa Convention Center, Tampa, Florida, USA. American Society of Agricultural Engineers, Tampa, USA, 2005.
[6] Burks T F, Shearer S A, Payne F A. Classification of weed species using color texture features and discriminant analysis. Transactions of the ASAE, 2000; 43: 441–448.
[7] Tang L, Tian L F, Steward B L. Classification of broadleaf and grass weeds and an artificial neural network. Transactions of the ASAE, 2003; 46: 1247–1254.
[8] Pydipati R, Bu Tang rks T F, Lee W S. Identification of citrus dis¬ease using color texture features and discriminant analysis. Comput. Electron. Agr., 2006; 52: 49–59.
[9] Du C J, Sun D W. Correlating image texture features ex-tracted by five different methods with the tenderness of cooked pork ham: a feasibility study. Transactions of the ASAE, 2006; 49: 441–448.
[10] Sun D W. Hyperspectral imaging for food quality analysis and control. Academic Press, Elsevier, San Diego, USA, 2006.
[11] Jiang L, Zhu B, Rao X, Berney G, Tao Y. Discrimination of black walnut shell and pulp in hyper spectral fluorescence imagery using Gaussian kernel function approach. J. Food Eng., 2007; 81: 108–117.
[12] Zhang Y, He X J, Han J H. Texture feature-based image classification using wavelet package transform. Advances in Intelligent Computing, 2005; 3644: 165–173.
[13] Kim M S, Chen Y R, Mehl P M. Hyperspectral reflectance and fluorescence imaging system for food quality and safety. Transactions of the ASAE, 2001; 44: 721–729.
[14] Lee K J, Kang S, Kim M S, Noh S H. Hyper-spectral imaging for detection defect on apple. paper no. 053075. In: ASAE Annual International Meeting. 17 July, Tampa Convention Center, Tampa, Florida, USA. American Society of Agricultural Engineers, Tampa, USA, 2005.
[15] Park B, Windham W R, Lawrence K C, Smith D P. Con-taminant classification of poultry hyperspectral imagery using a spectral angle mapper algorithm. Biosyst. Eng., 2007; 96: 323–333.
[16] Qin J, Burks T F, Ritenour M A, Bonn W G. Detection of citrus canker using hyperspectral reflectance imaging with spectral information divergence. J. Food Eng., 2009; 93: 183–191.
[17] Yang C, Everitt J H, Bradford J M. Yield estimation from hyperspectral imagery using spectral angle mapper (SAM). Transactions of the ASABE, 2008; 51: 729–737.
[18] Shippert P. Introduction to hyperspectral image analysis. Available from http://spacejournal.ohio.edu/pdf/shippert.pdf. Accessed on [2011-07-15].
[19] Du Y, Chang C I, Ren H, Chang C C, Jensen J O. New hyperspectral discrimination measure for spectral characterization. Opt. Eng., 2004; 43: 1777–1788.
[20] Chang C I. Spectral information divergence for hyperspectral image analysis. In: International Geoscience and Remote Sensing Symposium. 28 June, Congress Center, Hamburg, Germany. IEEE Publications, Hamburg, Germany, 1999; pp. 509–511.
Downloads
Published
2014-12-30
How to Cite
Kim, D., Burks, T. F., Ritenour, M. A., & Qin, J. (2014). Citrus black spot detection using hyperspectral imaging. International Journal of Agricultural and Biological Engineering, 7(6), 20–27. Retrieved from https://ijabe.migration.pkpps03.publicknowledgeproject.org/index.php/ijabe/article/view/1143
Issue
Section
Information Technology, Sensors and Control Systems
License
IJABE is an international peer reviewed open access journal, adopting Creative Commons Copyright Notices as follows.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
