Welcome to Chinese Agricultural Science Bulletin,

Chinese Agricultural Science Bulletin ›› 2020, Vol. 36 ›› Issue (30): 158-164.doi: 10.11924/j.issn.1000-6850.casb20191100813

Previous Articles    

The Application of Machine Learning in Crop Variety Recognition: A Review

Yang Lingyan(), Zhang Hongyan(), Chen Yufeng, Liu Yawen   

  1. College of Information and Intelligent Science and Technology, Hunan Agricultural University, Changsha 410128
  • Received:2019-11-08 Revised:2019-11-29 Online:2020-10-25 Published:2020-10-16
  • Contact: Zhang Hongyan E-mail:yly819@foxmail.com;hongyan_zhang@hunau.edu.cn

Abstract:

The successful application of machine learning in the field of image recognition provides a new idea for the automatic recognition of crop varieties. In order to fully understand the application status of machine learning in crop variety recognition and grasp the development trend and research direction of crop variety recognition, this paper summarized the common acquisition methods of crop image, and analyzed the research status of crop varieties recognition based on spectral image and RGB image with machine learning methods. The research on crop variety recognition based on RGB images started earlier, the cost of image acquisition is relatively low, and the recognition rate is general; the research on crop variety recognition based on hyperspectral images has developed rapidly in recent years, and the recognition accuracy is relatively high, but the cost of image acquisition is higher and easily affected by environmental factors. Through the summary, the existing problems in crop variety recognition research are pointed out, and it is considered that deep learning has a wide application prospect in the automatic recognition of crop varieties.

Key words: machine learning, spectral image, RGB image, crop variety recognition, image classification

CLC Number: