Automatic recognition of flower species in the natural environment

作者：

Highlights：

• Multi-layer technique for recognition and retrieval of flower species

• Method for image capture of flower object as well as background

• Developed flower image auto-recognition technology for use in mobile environment

• Experimental analysis of feature extraction by color, texture, and shape

• Verified at above 90% accuracy with 29,463 images of 300 flower species

摘要

•Multi-layer technique for recognition and retrieval of flower species•Method for image capture of flower object as well as background•Developed flower image auto-recognition technology for use in mobile environment•Experimental analysis of feature extraction by color, texture, and shape•Verified at above 90% accuracy with 29,463 images of 300 flower species

论文关键词：Flower image,Automatic recognition,Mobile,Natural environment,Random Forests

论文评审过程：Received 4 April 2015, Revised 25 November 2016, Accepted 9 January 2017, Available online 2 March 2017, Version of Record 28 March 2017.

论文官网地址：https://doi.org/10.1016/j.imavis.2017.01.013