Advertisement

Multimedia Tools and Applications

, Volume 77, Issue 17, pp 22821–22839 | Cite as

Twelve-layer deep convolutional neural network with stochastic pooling for tea category classification on GPU platform

  • Yu-Dong Zhang
  • Khan Muhammad
  • Chaosheng Tang
Article

Abstract

Automatic tea-category identification is an important topic in factories and supermarkets. Traditional methods need to extract features from tea images manually, which may not be optimal for tea images classification. To avoid the time consuming efforts of handcrafted features extraction, this study proposed a new method combining convolutional neural network (CNN) with stochastic pooling. We collected 900 tea images of Oolong, green, and black teas, with 300 images for each category. The data augmentation method was used over the training set. We employed stochastic gradient descent with momentum (SGDM) to train the CNN. The experiments showed that a 12-layer CNN gives a good result. The sensitivities of Oolong, green, and black tea are 99.5%, 97.5%, and 98.0%, respectively. The overall accuracy of all three-tea categories is 98.33%. The stochastic pooling gives better results than maximum pooling and average pooling. The optimal number of convolutional layer for this task is 5. In addition, GPU has a 175× acceleration in training set and a 122× acceleration in test set, compared to CPU platform.

Keywords

Convolutional neural network Stochastic pooling Data augmentation Tea category classification Stochastic gradient descent with momentum 

Notes

Acknowledgements

This paper is supported by Open fund of Key Laboratory of Guangxi High Schools Complex System and Computational Intelligence (2016CSCI01), Natural Science Foundation of China (61502254, 61602250), Program of Natural Science Research of Jiangsu Higher Education Institutions (15KJB470010, 16KJB520025), Natural Science Foundation of Jiangsu Province (BK20150983).

Compliance with ethical standards

Conflict of interest

There is no conflict of interest regarding the submission of this paper.

References

  1. 1.
    Altun M, Pekcan O (2017) A modified approach to cross entropy method: Elitist stepped distribution algorithm. Appl Soft Comput 58:756–769CrossRefGoogle Scholar
  2. 2.
    Barushka A, Hajek P (2016) Spam Filtering Using Regularized Neural Networks with Rectified Linear Units. In: 15th International Conference of the Italian Association for Artificial Intelligence (AIIA). Springer Int Publishing Ag, Genova, p 65–75Google Scholar
  3. 3.
    Chen Q (2008) Identification of tea varieties using computer vision. Trans ASABE 51(2):623–628CrossRefGoogle Scholar
  4. 4.
    Chen Y (2017) A Feature-Free 30-Disease Pathological Brain Detection System by Linear Regression Classifier. CNS Neurol Disord Drug Targets 16(1):5–10CrossRefGoogle Scholar
  5. 5.
    Chen QS et al (2013) Classification of tea category using a portable electronic nose based on an odor imaging sensor array. J Pharm Biomed Anal 84:77–89CrossRefGoogle Scholar
  6. 6.
    de Almeida CRF et al (2016) Satisficing Game Approach to Collaborative Decision Making Including Airport Management. IEEE Trans Intell Transp Syst 17(8):2262–2271CrossRefGoogle Scholar
  7. 7.
    Du S (2016) Multi-objective path finding in stochastic networks using a biogeography-based optimization method. Simulation 92(7):637–647CrossRefGoogle Scholar
  8. 8.
    Du S (2017) Alzheimer's Disease Detection by Pseudo Zernike Moment and Linear Regression Classification. CNS Neurol Disord Drug Targets 16(1):11–15CrossRefGoogle Scholar
  9. 9.
    Fernando B et al (2017) Rank Pooling for Action Recognition. IEEE Trans Pattern Anal Mach Intell 39(4):773–787CrossRefGoogle Scholar
  10. 10.
    Ferreira A, Giraldi G (2017) Convolutional Neural Network approaches to granite tiles classification. Expert Syst Appl 84:1–11CrossRefGoogle Scholar
  11. 11.
    Ferreira MD et al (2018) Designing architectures of convolutional neural networks to solve practical problems. Expert Syst Appl 94:205–217CrossRefGoogle Scholar
  12. 12.
    Gorriz JM, Ramírez J (2016) Wavelet entropy and directed acyclic graph support vector machine for detection of patients with unilateral hearing loss in MRI scanning. Front Comput Neurosci 10:160Google Scholar
  13. 13.
    Gummeson A et al (2017) Automatic Gleason grading of HE stained microscopic prostate images using deep convolutional neural networks. In: Medical Imaging 2017, Digital Pathology, 2017, 10140.  https://doi.org/10.1117/12.2253620
  14. 14.
    Ji G (2014) Fruit classification using computer vision and feedforward neural network. J Food Eng 143:167–177CrossRefGoogle Scholar
  15. 15.
    Jia W (2017) Three-Category Classification of Magnetic Resonance Hearing Loss Images Based on Deep Autoencoder. J Med Syst 41:165CrossRefGoogle Scholar
  16. 16.
    Jian W, Xianyin Z, ShiPing D (2010) Identification and grading of tea using computer vision. Appl Eng Agric 26(4):639–645CrossRefGoogle Scholar
  17. 17.
    Jiang Y et al (2017) Cerebral Micro-Bleed Detection Based on the Convolution Neural Network With Rank Based Average Pooling. IEEE Access 5:16576–16583CrossRefGoogle Scholar
  18. 18.
    Kabani A, El-Sakka MR (2016) Object Detection and Localization Using Deep Convolutional Networks with Softmax Activation and Multi-class Log Loss. In: 13th International Conference on Image Analysis and Recognition in Memory of Mohamed Kamel (ICIAR). Springer Int Publishing Ag, Povoa de Varzim, p 358–366Google Scholar
  19. 19.
    Li XL, Zhang YY, He Y (2017) Study on Detection of Talcum Powder in Green Tea Based on Fourier Transform Infrared (FTIR) Transmission Spectroscopy. Spectrosc Spectr Anal 37(4):1081–1085Google Scholar
  20. 20.
    Liu A (2017) Tea Category Identification using Computer Vision and Generalized Eigenvalue Proximal SVM. Fundam Inform 151(1–4):325–339MathSciNetGoogle Scholar
  21. 21.
    Lu S, Lu Z (2016) A pathological brain detection system based on kernel based ELM. Multimed Tools Appl.  https://doi.org/10.1007/s11042-016-3559-z
  22. 22.
    Martinez-Pabon F et al (2016) Recommending Ads from Trustworthy Relationships in Pervasive Environments. Mob Inf Syst 2016:8593173Google Scholar
  23. 23.
    Pan H, Zhang C, Tian Y (2014) RGB-D image-based detection of stairs, pedestrian crosswalks and traffic signs. J Vis Commun Image Represent 25(2):263–272CrossRefGoogle Scholar
  24. 24.
    Pezeshk A et al (2017) Seamless Lesion Insertion for Data Augmentation in CAD Training. IEEE Trans Med Imaging 36(4):1005–1015CrossRefGoogle Scholar
  25. 25.
    Saha P et al (2017) Feature Fusion for Prediction of Theaflavin and Thearubigin in Tea Using Electronic Tongue. IEEE Trans Instrum Meas 66(7):1703–1710CrossRefGoogle Scholar
  26. 26.
    Sun M et al (2016) Max-pooling loss training of long short-term memory networks for small-footprint keyword spotting. In: IEEE workshop on spoken language technology (SLT). IEEE, San Diego, p 474–480Google Scholar
  27. 27.
    Tang Z et al (2015) A local binary pattern based texture descriptors for classification of tea leaves. Neurocomputing 168:1011–1023CrossRefGoogle Scholar
  28. 28.
    Wei L, Yang J (2016) Fitness-scaling adaptive genetic algorithm with local search for solving the Multiple Depot Vehicle Routing Problem. Simulation 92(7):601–616CrossRefGoogle Scholar
  29. 29.
    Wu X (2016) Tea category identification based on optimal wavelet entropy and weighted k-Nearest Neighbors algorithm. Multimed Tools Appl.  https://doi.org/10.1007/s11042-016-3931-z
  30. 30.
    Yang J (2015) Identification of green, Oolong and black teas in China via wavelet packet entropy and fuzzy support vector machine. Entropy 17(10):6663–6682Google Scholar
  31. 31.
    Yang J (2017) Pathological brain detection in MRI scanning via Hu moment invariants and machine learning. J Exp Theor Artif Intell 29(2):299–312CrossRefGoogle Scholar
  32. 32.
    Zeiler M, Fergus R (2013) Stochastic pooling for regularization of deep convolutional neural networks. In Proceedings of the International Conference on Learning Representation (ICLR)Google Scholar
  33. 33.
    Zhan TM, Chen Y (2016) Multiple Sclerosis Detection Based on Biorthogonal Wavelet Transform, RBF Kernel Principal Component Analysis, and Logistic Regression. IEEE Access 4:7567–7576MathSciNetCrossRefGoogle Scholar
  34. 34.
    Zhou X (2016) Tea Category Classification Based on Feed-Forward Neural Network and Two-Dimensional Wavelet Entropy. In: Xie J et al (eds) Third International Conference on High Performance Computing and Applications. Springer International Publishing, Cham, pp 48–54CrossRefGoogle Scholar
  35. 35.
    Zhu SG, Du JP (2014) Visual Tracking Using Max-Average Pooling and Weight-Selection Strategy. J Appl Math 2014:828907Google Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Department of InformaticsUniversity of LeicesterLeicesterUK
  2. 2.School of Computer Science and TechnologyHenan Polytechnic UniversityJiaozuoPeople’s Republic of China
  3. 3.Digital Contents Research InstituteSejong UniversitySeoulRepublic of Korea

Personalised recommendations