Disease classification in Solanum melongena using deep learning

  • Krishnaswamy R. Aravind SASTRA Deemed University, School of Mechanical Engineering, Thanjavur 613401, Tamil Nadu
  • Purushothaman Raja SASTRA Deemed University, School of Mechanical Engineering, Thanjavur 613401, Tamil Nadu
  • Rajendran Ashiwin SASTRA Deemed University, School of Mechanical Engineering, Thanjavur 613401, Tamil Nadu
  • Konnaiyar V. Mukesh SASTRA Deemed University, School of Mechanical Engineering, Thanjavur 613401, Tamil Nadu
Keywords: convolutional neural network, Tobacco mosaic virus disease, Epilachna beetle, Little leaf, Cercospora leaf spot, two-spotted spider mite, transfer learning

Abstract

Aim of study: The application of pre-trained deep learning models, AlexNet and VGG16, for classification of five diseases (Epilachna beetle infestation, little leaf, Cercospora leaf spot, two-spotted spider mite and Tobacco Mosaic Virus (TMV)) and a healthy plant in Solanum melongena (brinjal in Asia, eggplant in USA and aubergine in UK) with images acquired from smartphones.

Area of study: Images were acquired from fields located at Alangudi (Pudukkottai district), Tirumalaisamudram and Pillayarpatti (Thanjavur district) – Tamil Nadu, India.

Material and methods: Most of earlier studies have been carried out with images of isolated leaf samples, whereas in this work the whole or part of the plant images were utilized for the dataset creation. Augmentation techniques were applied to the manually segmented images for increasing the dataset size. The classification capability of deep learning models was analysed before and after augmentation. A fully connected layer was added to the architecture and evaluated for its performance.

Main results: The modified architecture of VGG16 trained with the augmented dataset resulted in an average validation accuracy of 96.7%. Despite the best accuracy, all the models were tested with sample images from the field and the modified VGG16 resulted in an accuracy of 93.33%.

Research highlights: The findings provide a guidance for possible factors to be considered in future research relevant to the dataset creation and methodology for efficient prediction using deep learning models.

Downloads

Download data is not yet available.

References

Agroreyo BO, Obansa ES, Obanor EO, 2012. Comparative nutritional and phytochemical analyses of two varieties of Solanum melongena. Sci World J 7 (1): 5-8.

Ali H, Lali MI, Nawaz MZ, Sharif M, Saleem BA, 2017. Symptom based automated detection of citrus diseases using color histogram and textural descriptors. Comput Electron Agric 138: 92-104. https://doi.org/10.1016/j.compag.2017.04.008

Alishiri A, Rakhshandehroo F, Zamanizadeh HR, Palukaitis P, 2013. Prevalence of tobacco mosaic virus in Iran and evolutionary analyses of the coat protein gene. Plant Pathol J 29 (3): 260-273. https://doi.org/10.5423/PPJ.OA.09.2012.0145

Aravind KR, Raja P, Aniirudh R, Mukesh KV, Ashiwin R, Vikas, 2018. Grape crop disease classification using transfer learning approach. Proc Int Conf on ISMAC in Computational Vision and Bio-Engineering, Palladam (India), May 16-17. pp: 1623-1633. https://doi.org/10.1007/978-3-030-00665-5_150

Arivazhagan S, Shebiah RN, Ananthi S, Varthini V, 2013. Detection of unhealthy region of plant leaves and classification of plant leaf diseases using texture features. Agric Eng Int: CIGR J 15 (1): 211-217.

Barbedo JGA, 2016. A review on the main challenges in automatic plant disease identification based on visible range images. Biosyst Eng 144: 52-60. https://doi.org/10.1016/j.biosystemseng.2016.01.017

Barbedo JGA, 2018a. Factors influencing the use of deep learning for plant disease recognition. Biosyst Eng 172: 84-91. https://doi.org/10.1016/j.biosystemseng.2018.05.013

Barbedo JGA, 2018b. Impact of dataset size and variety on the effectiveness of deep learning and transfer learning for plant disease classification. Comput Electron Agric 153: 46-53. https://doi.org/10.1016/j.compag.2018.08.013

Barbedo JGA, Koenigkan LV, Santos TT, 2016. Identifying multiple plant diseases using digital image processing. Biosyst Eng 147: 104-116. https://doi.org/10.1016/j.biosystemseng.2016.03.012

Beale MH, Hagan MT, Demuth HB, 2018. Neural Network ToolboxTM User's Guide. The MathWorks.Inc, Natick, MA, USA.

Brahimi M, Boukhalfa K, Moussaoui A, 2017. Deep learning for tomato diseases: classification and symptoms visualization. Appl Artif Intell 31: 299-315. https://doi.org/10.1080/08839514.2017.1315516

Brahimi M, Aresenovic M, Laraba S, Sladojevic S, Boukhalfa K, Moussaoui A, 2018. Deep learning for plant diseases: Detection and saliency map visualisation. In: Human and machine learning. Human-Computer Interaction Series; Zhou J, Chen F. (eds.). pp: 93-117. Springer, Cham. https://doi.org/10.1007/978-3-319-90403-0_6

Calderón R, Navas-Cortés JA, Lucena C, Zarco-Tejada PJ, 2013. High-resolution airborne hyperspectral and thermal imagery for early detection of Verticillium wilt of olive using fluorescence, temperature and narrow-band spectral indices. Rem Sens Environ 139: 231-245. https://doi.org/10.1016/j.rse.2013.07.031

De Castro AI, Ehsani R, Ploetz R, Cran JH, Abdulridha J, 2015. Optimum spectral and geometric parameters for early detection of laurel wilt disease in avocado. Rem Sens Environ 171: 33-44. https://doi.org/10.1016/j.rse.2015.09.011

Dey AK, Sharma M, Meshram MR, 2016. Image processing based leaf rot disease, detection of betel vine (Piper Betle L.). Procedia Comput Sci 85: 747-754. https://doi.org/10.1016/j.procs.2016.05.262

Dhakad KK, 2017. Epidemiology and management of eggplant diseases in Jabalpur, Madhya Pradesh. Master's thesis. Jawaharlal Nehru Krishi Vishwa Vidyalaya, Jabalpur, India.

Ferentinos KP, 2018. Deep learning models for plant disease detection and diagnosis. Comput Electron Agr 145: 311-318. https://doi.org/10.1016/j.compag.2018.01.009

García-Ruiz F, Sankaran S, Maja JM, Lee WS, Rasmussen J, Ehsani R, 2013. Comparison of two aerial imaging platforms for identification of Huanglongbing-infected citrus trees. Comput Electron Agr 91: 106-115. https://doi.org/10.1016/j.compag.2012.12.002

Hunter D, Yu H, Pukish MS, Kolbusz J, Wilamowski BM, 2012. Selection of proper neural network sizes and architecture- a comparative study. IEEE Trans Ind Inform 8 (2): 228-240. https://doi.org/10.1109/TII.2012.2187914

Krizhevsky A, Sutskever I, Hinton GE, 2012. Imagenet classification with deep convolution neural networks. Proc of Advances in Neural Information Processing Systems, Lake Tahoe (USA), May 3-8. pp: 1097-1105.

Kruse OMO, Montalbán JMP, Indahl UG, Kvaal K, Ferrer A, Futsaether CM, 2014. Pixel classification methods for identifying and quantifying leaf surface injury from digital images. Comput Electron Agr 108: 155-165. https://doi.org/10.1016/j.compag.2014.07.010

Liu B, Zhang Y, He D, Li Y, 2018. Identification of apple leaf diseases based on deep convolutional neural networks. Symmetry 10 (1): 11. https://doi.org/10.3390/sym10010011

Lu Y, Yi S, Zeng N, Liu Y, Zhang Y, 2017. Identification of rice disease using deep convolutional neural networks. Neuro Comput 267: 378-384. https://doi.org/10.1016/j.neucom.2017.06.023

Ma J, Du K, Zheng F, Zhang L, Gong Z, Sun Z, 2018. A recognition method for cucumber disease using leaf symptom images based on deep convolutional neural network. Comput Electron Agr 154:18-24. https://doi.org/10.1016/j.compag.2018.08.048

Madzokere ET, 2017. History of the emergence and spatiotemporal spread of tobacco mosaic virus in China. Virol Mycol 6 (2): Art ID 171.

Mohanchander P, Reegan AD, Rahman MAU, Raveen RS, 2013. Effect of hadda beetle, Epliachna vigintioctopunctata Fab. (Coleoptera: Coccinellidae) infestation on eggplant leaf (Solanum melongena L.) and bio-control potential of essential oil formulations. Pak J Biol Sci 16 (19): 991-997. https://doi.org/10.3923/pjbs.2013.991.997

Mohanty SP, Hughes DP, Salathe M, 2016. Using deep learning for image-based plant disease detection. Front Plant Sci 7: Art ID 149. https://doi.org/10.3389/fpls.2016.01419

Pilli SK, Nallathambi B, George SJ, Diwanji V, 2014. eAGROBOT - A robot for early crop disease detection using image processing. IEEE Int Conf on Electronics and Communication Systems; February. pp: 1-6. https://doi.org/10.1109/ECS.2014.7090754

Polder G, van der Heijden GWAM, van Doorn J, Baltissen TAHMC, 2014. Automatic detection of tulip breaking virus (TBV) in tulip fields using machine vision. Biosyst Eng 117: 35-42. https://doi.org/10.1016/j.biosystemseng.2013.05.010

Ramaraju K, 2004. Evaluation of acaricides and TNAU neem oils against spider mite, Tetranychus urticae (Koch) on bhendi and brinjal. Madras Agric J 91: 7-12.

Rao GP, Madhupriya, Thorat V, Manimekalai R, Tiwari AK, Yadav A, 2017. A century progress of research on phytoplasma disease in India. Phytopathog Mollicutes 7 (1): 1-38. https://doi.org/10.5958/2249-4677.2017.00001.9

Salgadoe ASA, Robson AJ, Lamb DW, Dann EK, Searle C, 2018. Quantifying the severity of phytophthora root rot disease in avocado tress using image analysis. Rem Sens 10 (2): 226. https://doi.org/10.3390/rs10020226

Schor N, Bechar A, Ignat T, Dombrovsky A, Elad Y, Bermann S, 2016. Robotic disease detection in greenhouse: Combined detection of powdery mildew and tomato spotted wilt virus. IEEE Robot Autom Lett 1 (1): 354-360. https://doi.org/10.1109/LRA.2016.2518214

Shazly MAE, Abagy EME, Aly AME, Youssef SA, 2016. Identification and molecular characterization of little leaf disease associated with Phytoplasma on sugar beet (Beta Vulgaris L.) plants in Egypt. Middle East J Appl Sci 6 (4): 1054-1065.

Simonyan K, Zisserman A, 2014. Very deep convolutional networks for large-scale image recognition. Int Conf on Learning Representations. April. http://arxiv.org/abs/1409.1556

Srinivasan R, 2009. Insect and mite pests on egg plants: A field guide for identification and management, AVRDC - The World Vegetable Center, Shanhua, Taiwan, AVRDC Publication No 09-729. 64 pp.

Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R, 2015. Dropout: a simple way to prevent neural network from overfitting. J Mach Learn 15: 1929-1958.

Srivastava S, Nelson S, 2012. Cercospora leaf spot of eggplant. Plant Dis 82: 1-5.

Story D, Kacira M, 2015. Design and implementation of a computer vision-guided greenhouse crop diagnostics system. Mach Vis Appl 26: 495-506. https://doi.org/10.1007/s00138-015-0670-5

Strange RN, Scott PR, 2005. Plant disease: A threat to global food security. Annu Rev Phytopathol 43: 83-116. https://doi.org/10.1146/annurev.phyto.43.113004.133839

Zhang S, Wu X, You Z, Zhang L, 2017. Leaf image based cucumber disease recognition using sparse representation classification. Comput Electron Agr 134: 135-141. https://doi.org/10.1016/j.compag.2017.01.014

Zhou R, Kaneko S, Tanaka F, Kayamori M, Shimizu M, 2014. Disease detection of Cercospora leaf spot in sugar beet by robust template matching. Comput Electron Agr 108: 58-70. https://doi.org/10.1016/j.compag.2014.07.004

Published
2019-11-08
How to Cite
Aravind, K. R., Raja, P., Ashiwin, R., & Mukesh, K. V. (2019). Disease classification in Solanum melongena using deep learning. Spanish Journal of Agricultural Research, 17(3), e0204. https://doi.org/10.5424/sjar/2019173-14762
Section
Agricultural engineering