CLASSIFIER OF IMAGES OF AGRICULTURAL CROPS SEEDS USING A CONVOLUTION NEURAL NETWORK
Abstract
This article discusses the creation of a convolutional neural network architecture that classifies
images of crops (in particular wheat) for subsequent use in an optical seed separator (photo
separator). Interest in the design of neural networks for classifying images has recently increased
significantly, which is associated both with the development of the theory of deep neural networks
and the increased computing power of desktop computers, as well as the transfer of computing to
graphic processors. The aim of the article is to develop the architecture of a neural network that
allows the separation of the input flow of wheat seeds into two classes: “good” seeds and “bad”
(with defects in shape and color) seeds. The architecture of the resulting neural network is convolutional,
because, unlike a fully connected one, this class of neural networks is within certain limits
immune to changes in the scale and angle of rotation of objects in the input data. In the work,
for the formation of training, validation and test samples, seed images obtained using a household
camera were used, which negatively affected the results of training and testing the neural network
regarding the possible result of application in a real photo separator. The architecture of the developed
neural network is preliminarily optimized for use on FPGAs, however, in the considered
case, the transition from the values of weighting factors from the data type from a floating point to
an integer type has not been made, which can lead to a decrease in the accuracy of the neural
network, while significantly reducing the amount of resources FPGA. Application of the proposed
architecture allows one to obtain a fairly accurate estimate of classified wheat seeds from verification
and test data sets.
References
from engl. Moscow: Tekhnosfera, 2005, 1073 p.
2. Anderson T.W., Goodman L.A. Statistical inference about Markov chains, The Annals of Mathematical
Statistics, 1957, pp. 89-110.
3. Vagis A.A. Protsedura raspoznavaniya na bayesovskikh setyakh, Komp'yuternaya matematika,
2010, No. 2, pp. 124-130.
4. LeCun Y. et al. Gradient-based learning applied to document recognition, Proceedings of the
IEEE, 1998, Vol. 86, Issue 11, pp. 2278-2324.
5. Gu J. et al. Recent advances in convolutional neural networks, Pattern Recognition, 2018,
Vol. 77, pp. 354-377.
6. Srinivas S. et al. A taxonomy of deep convolutional neural nets for computer vision, Frontiers
in Robotics and AI, 2016, Vol. 2, pp. 36.
7. Glorot X., Bengio Y. Understanding the difficulty of training deep feedforward neural networks,
Proceedings of the thirteenth international conference on artificial intelligence and statistics,
2010, pp. 249-256.
8. He K. et al. Delving deep into rectifiers: Surpassing human-level performance on imagenet
classification, Proceedings of the IEEE international conference on computer vision, 2015, pp.
1026-1034.
9. LeCun Y. et al. Backpropagation applied to handwritten zip code recognition, Neural computation,
1989, Vol. 1, Issue 4, pp. 541-551.
10. Boureau Y.L. et al. Learning mid-level features for recognition, 2010 IEEE Computer Society
Conference on Computer Vision and Pattern Recognition. IEEE, 2010, pp. 2559-2566.
11. Scherer D., Müller A., Behnke S. Evaluation of pooling operations in convolutional architectures
for object recognition, International conference on artificial neural networks. Springer,
Berlin, Heidelberg, 2010, pp. 92-101.
12. Boureau Y.L., Ponce J., LeCun Y. A theoretical analysis of feature pooling in visual recognition,
Proceedings of the 27th international conference on machine learning (ICML-10), 2010,
pp. 111-118.
13. Krizhevsky A., Sutskever I., Hinton G.E. Imagenet classification with deep convolutional neural
networks, Advances in neural information processing systems, 2012, pp. 1097-1105.
14. Maas A.L., Hannun A.Y., Ng A.Y. Rectifier nonlinearities improve neural network acoustic
models, Proc. icml., 2013, Vol. 30, Issue No. 1, pp. 3.
15. Zeiler M.D. et al. On rectified linear units for speech processing, 2013 IEEE International
Conference on Acoustics, Speech and Signal Processing. IEEE, 2013, pp. 3517-3521.
16. Kalman B.L., Kwasny S.C. Why tanh: choosing a sigmoidal function, [Proceedings 1992]
IJCNN International Joint Conference on Neural Networks. IEEE, 1992, Vol. 4, pp. 578-581.
17. Marra S., Iachino M.A., Morabito F.C. Tanh-like activation function implementation for highperformance
digital neural systems, 2006 Ph. D. Research in Microelectronics and Electronics.
IEEE, 2006, pp. 237-240.
18. Cortes C., Mohri M., Rostamizadeh A. L2 regularization for learning kernels, arXiv preprint
arXiv:1205.2653, 2012.
19. Tikhonov A.N. O nekorrektnykh zadachakh lineynoy algebry i ustoychivom metode ikh
resheniya [On ill – posed linear algebra problems and a stable method for solving
them], DAN SSSR [Reports of the Academy of Sciences of USSR], 1965, Vol. 163, No. 3,
pp. 591-594.
20. Kingma D.P., Ba J. Adam: A method for stochastic optimization, arXiv preprint
arXiv:1412.6980, 2014.
21. Wang J. et al. Design flow of accelerating hybrid extremely low bit-width neural network in
embedded FPGA, 2018 28th International Conference on Field Programmable Logic and Applications
(FPL). IEEE, 2018, pp. 163-1636.
