Detection of White Ear-Head of Rice Crop Using Image Processing and Machine Learning Techniques

  • Prabira Kumar SethyEmail author
  • Smitanjali Gouda
  • Nalinikanta Barpanda
  • Amiya Kumar Rath
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 766)


Farmers in rural India have minimal access to agriculture aspect that can inspect paddy crop images and provide advice. Expert advice responses to queries often reach farmers too late. The disease in paddy crop mostly affects leaf and panicle. The disease that affects the panicle is more severe than the other parts of the paddy crop, as it directly hampers the production. Owing to the infestation of stem borer at the time of ear-head emergence, panicle gets dried and turns white in color, which is known as white ear-head. Automatic detection of white ear-head is done based on high-resolution images captured through mobile camera. In our proposed methodology, we analyze the image of defected panicle by using advanced image processing technique with machine learning to identify whether a panicle is white ear-head affected or a healthy one. This paper executes three machine learning techniques, that is PCA, Gabor filter and ANN, with an accuracy of 85, 90 and 95%, respectively.


PCA Gabor filter ANN White ear-head 


  1. 1.
    Hand Book on Rice Cultivation and Processing by NPCS Board of Consultants and Engineers. ISBN: 978-81-905685-2-4Google Scholar
  2. 2.
    do Espírito Santo, R.: Principal Component Analysis applied to digital image compression, Instituto do Cérebro - InCe, Hospital Israelita Albert Einstein – HIAE, São Paulo (SP), BrazilGoogle Scholar
  3. 3.
    Al-Kadi, O.S.: A Gabor Filter Texture Analysis Approach For Histopathological Brain Tumour Subtype Discrimination, King Abdullah II, School for Information Technology, University of Jordan Amman, 11942, JordanGoogle Scholar
  4. 4.
    Grigorescu, S.E., Petkov, N., Kruizinga, P.: Comparison of texture features based on Gabor filters. IEEE Trans. Image Process. 11(10), 1160–1167 (2002)MathSciNetCrossRefGoogle Scholar
  5. 5.
    Dongare, A.D., Kharde, R.R., Kachare, A.D.: Introduction to artificial neural network. Int. J. Eng. Innov. Technol. (IJEIT) 2(1) (2012)Google Scholar
  6. 6.
    Liu, Z.Y., Huang, J.F., Shi, J.J., Tao, R.X., Zhou, W., Zhang, L.L.: Characterizing and estimating rice brown spot disease severity using stepwise regression, principal component regression and partial least-square regression. J. Zhejiang. Univ. Sci. B. 8(10), 738–744 (2007). Scholar
  7. 7.
    Huang, S., Qi, L., Ma, X., Xue, K., Wang, W., Zhu, X.: Hyperspectral image analysis based on BoSW model for rice panicle blast grading. Comput. Electron. Agricu. 118, 167–178 (2015). Scholar
  8. 8.
    Kumar, A., Zhang, D.: Personal authentication using multiple palm print representation. Pattern Recognit. 38(10), 1695–1704 (2005). Scholar
  9. 9.
    Liu, Z., Shi, J., Zhang, L., Huang, J.: Discrimination of rice panicles by hyperspectral reflectance data based on principal component analysis and support vector classification. J. Zhejiang. Univ. Sci. 11(1), 71–78 (2010). Scholar
  10. 10.
    Siddhichai, S., Watcharapinchai, N., Aramvith, S., Marukatat, S.: Dimensionality reduction of SIFT using PCA for object categorization. In: International Symposium on Intelligent Signal Processing and Communication Systems, May 2008Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  • Prabira Kumar Sethy
    • 1
    Email author
  • Smitanjali Gouda
    • 1
  • Nalinikanta Barpanda
    • 1
  • Amiya Kumar Rath
    • 2
  1. 1.Department of ElectronicsSambalpur UniversitySambalpurIndia
  2. 2.Department of Computer Science and EngineeringVSSUTBurlaIndia

Personalised recommendations