The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download

The requested paper has a corresponding corrigendum published. Please read the corrigendum first before downloading the article.

Publications Copernicus
Download
Notice on corrigendum

The requested paper has a corresponding corrigendum published. Please read the corrigendum first before downloading the article.

Citation
Articles | Volume XLII-3/W6
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-3/W6, 631–635, 2019
https://doi.org/10.5194/isprs-archives-XLII-3-W6-631-2019
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-3/W6, 631–635, 2019
https://doi.org/10.5194/isprs-archives-XLII-3-W6-631-2019

  26 Jul 2019

26 Jul 2019

RICE PLANT DISEASE CLASSIFICATION USING TRANSFER LEARNING OF DEEP CONVOLUTION NEURAL NETWORK

V. K. Shrivastava1, M. K. Pradhan2, S. Minz3, and M. P. Thakur4 V. K. Shrivastava et al.
  • 1School of Electronics Engineering, KIIT, Bhubaneswar, India
  • 2Department of Agricultural Statistics & Computer Science, IGKV, Raipur, India
  • 3School of Computer & Systems Sciences, JNU, New Delhi, India
  • 4Department of Plant Pathology, IGKV, Raipur, India

Keywords: Classification, CNN, Deep Learning, Pattern Recognition, Rice Plant Disease, Transfer Learning

Abstract. Early and accurate diagnosis of plant diseases is a vital step in the crop protection system. In traditional practices, identification is performed either by visual observation or by testing in laboratory. The visual observation requires expertise and it may vary subject to an individual which may lead to an error while the laboratory test is time consuming and may not be able to provide the results in time. To overcome these issues, image based machine learning approach to detect and classify plant diseases has been presented in literature. We have focused specifically on rice plant (Oryza sativa) disease in this paper. The images of the diseased symptoms in leaves and stems have been captured from the rice field. We have collected a total of 619 rice plant diseased images from the real field condition belong to four classes:(a) Rice Blast (RB), (b) Bacterial Leaf Blight (BLB), (c) Sheat Blight (SB) and (d) Healthy Leave (HL). We have used a pre-trained deep convolutional neural network(CNN) as a feature extractor and Support Vector Machine (SVM) as a classifier. We have obtained encouraging results. The early identification of rice diseases by this approach could be used as a preventive measure well as an early warning system. Further, it could be extended to develop a rice plant disease identification system on real agriculture field.

Please read the corrigendum first before accessing the article.