Capsule network with K-Means routingfor plant disease recognition

Capsule Networks (CapsNets) excel on simple image recognition problems. However, they fail to perform on complex images with high similarity and background objects. This paper proposes Local Binary Pattern (LBP) k-means routing and evaluates its performance on three publicly available plant disease datasets containing images with high similarity and background objects. The proposed routing algorithm adopts the squared Euclidean distance, sigmoid function, and a ‘simple-squash’ in place of dot product, SoftMax normalizer, and the squashing function found respectively in the dynamic routing algorithm. Extensive experiments conducted on the three datasets showed that the proposed model achieves consistent improvement in test accuracy across the three datasets as well as allowing an increase in the number of routing iterations with no performance degradation. The proposed model outperformed a baseline CapsNet by 8.37% on the tomato dataset with an overall test accuracy of 98.80%, comparable to state-of-the-art models on the same datasets.

[1]  T. M. Prajwala,et al.  Tomato Leaf Disease Detection Using Convolutional Neural Networks , 2018, 2018 Eleventh International Conference on Contemporary Computing (IC3).

[2]  Bohan Jia,et al.  DE-CapsNet: A Diverse Enhanced Capsule Network with Disperse Dynamic Routing , 2020 .

[3]  Matti Pietikäinen,et al.  Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  S. Chakraborty,et al.  Climate change and plant disease management. , 1999, Annual review of phytopathology.

[5]  Michael I. Jordan,et al.  Learning with Mixtures of Trees , 2001, J. Mach. Learn. Res..

[6]  Tingting Su,et al.  Image Recognition of Peanut Leaf Diseases Based on Capsule Networks , 2019 .

[7]  Liwei Sun,et al.  Proteomic Analyses Provide Novel Insights into Plant Growth and Ginsenoside Biosynthesis in Forest Cultivated Panax ginseng (F. Ginseng) , 2016, Front. Plant Sci..

[8]  Konstantinos P. Ferentinos,et al.  Deep learning models for plant disease detection and diagnosis , 2018, Comput. Electron. Agric..

[9]  Jin Liu,et al.  Multi-Lane Capsule Network for Classifying Images With Complex Background , 2020, IEEE Access.

[10]  Rika Sustika,et al.  Deep Structured Convolutional Neural Network for Tomato Diseases Detection , 2018, 2018 International Conference on Advanced Computer Science and Information Systems (ICACSIS).

[11]  Shan Cao,et al.  E2-Capsule Neural Networks for Facial Expression Recognition Using AU-Aware Attention , 2019, IET Image Process..

[12]  Keke Zhang,et al.  Can Deep Learning Identify Tomato Leaf Disease? , 2018, Adv. Multim..

[13]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[14]  Amit Prakash Singh,et al.  Exploring capsule networks for disease classification in plants , 2020 .

[15]  Geoffrey E. Hinton,et al.  Transforming Auto-Encoders , 2011, ICANN.

[16]  Joseph Zelina,et al.  Progress in Aero-Engine Technology, 1939-2003 (invited) , 2003 .

[17]  Adebayo Felix Adekoya,et al.  Capsule Networks - A survey , 2019, J. King Saud Univ. Comput. Inf. Sci..

[18]  Murvet Kirci,et al.  Disease detection on the leaves of the tomato plants by using deep learning , 2017, 2017 6th International Conference on Agro-Geoinformatics.

[19]  Raja Purushothaman,et al.  Tomato crop disease classification using pre-trained deep learning algorithm , 2018 .

[20]  Ramar Ahila Priyadharshini,et al.  Maize leaf disease classification using deep convolutional neural networks , 2019, Neural Computing and Applications.

[21]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[22]  Syed Ahmad Chan Bukhari,et al.  A citrus fruits and leaves dataset for detection and classification of citrus diseases through machine learning , 2019, Data in brief.

[23]  Marcel Salathé,et al.  Using Deep Learning for Image-Based Plant Disease Detection , 2016, Front. Plant Sci..

[24]  Abdelouahab Moussaoui,et al.  Deep Learning for Tomato Diseases: Classification and Symptoms Visualization , 2017, Appl. Artif. Intell..

[25]  Fumio Okura,et al.  How Convolutional Neural Networks Diagnose Plant Disease , 2019, Plant phenomics.

[26]  Marcel Salathé,et al.  An open access repository of images on plant health to enable the development of mobile disease diagnostics through machine learning and crowdsourcing , 2015, ArXiv.

[27]  Faculdade de Engenharia,et al.  Computational Vision and Bio-Inspired Computing , 2020 .

[28]  Mosin Hasan,et al.  Deep Learning Precision Farming: Tomato Leaf Disease Detection by Transfer Learning , 2019, SSRN Electronic Journal.

[29]  Sang Cheol Kim,et al.  A Robust Deep-Learning-Based Detector for Real-Time Tomato Plant Diseases and Pests Recognition , 2017, Sensors.