The recognition of rice images by UAV based on capsule network
- 1.5k Downloads
It is important to recognize the rice image captured by unmanned aerial vehicle (UAV) for monitoring the growth of rice and preventing the diseases and pests. Aiming at the image recognition, we use rice images captured by UAV as our data source, the structure of capsule network (CapsNet) is built to recognize rice images in this paper. The images are preprocessed through histogram equalization method into grayscale images and through superpixel algorithm into the superpixel segmentation results. The both results are output into the CapsNet. The function of CapsNet is to perform the reverse analysis of rice images. The CapsNet consists of five layers: an input layer, a convolution layer, a primary capsules layer, a digital capsules layer and an output layer. The CapsNet trains classification and predicts the output vector based on routing-by-agreement protocol. Therefore, the features of rice image by UAV can be precisely and efficiently extracted. The method is more convenient than the traditional artificial recognition. It provides the scientific support and reference for decision-making process of precision agriculture.
KeywordsImage recognition Capsule network Feature extraction Routing-by-agreement protocol
This paper is acknowledged by the National Natural Science Foundation of China (Grant No. 51502209), the Government Support Enterprise Development Funding of Hubei Province (Grant No. 16441), the Three-dimensional Textiles Engineering Research Center of Hubei Province, the Anqing Technology Transfer Center of Wuhan Textile University.
- 2.Schmidt, D.F., Botwinick, J.: UAV-based imaging for multi-temporal, very high resolution crop surface models to monitor crop growth variability. Photogrammetrie-Fernerkundung-Geoinformation 6(6), 551–562 (2013)Google Scholar
- 10.Latte, M.V., Shidnal, S., Anami, B.S., et al.: A combined HSV and GLCM approach for paddy variety identification from crop images. Int. J. Signal Process. Image Process. Pattern Recognit. 8 (2015)Google Scholar
- 14.Sabour, S., Frosst, N., Hinton, G.E.: Dynamic routing between capsules. arXiv:1710.09829.2017
- 15.Shin, M., Kim, M., Kwon, D.S.: Baseline CNN structure analysis for facial expression recognition. In: Robot and Human Interactive Communication (RO-MAN), 2016 25th IEEE International Symposium on, pp. 724–729 (2016)Google Scholar
- 17.Achanta, R., Shaji, A., Smith, K., et al.: SLIC superpixels. Epfl (2010)Google Scholar
- 19.Hsu, C.Y., Ding, J.J.: Efficient image segmentation algorithm using SLIC superpixels and boundary-focused region merging, pp. 1–5. In: Communications and Signal Processing. IEEE (2013)Google Scholar
- 20.Dubey, S.R., Jalal, A.S.: Detection and classification of apple fruit diseases using complete local binary patterns. In: Third International Conference on Computer and Communication Technology, pp. 346–351. IEEE Computer Society (2012)Google Scholar