A Flower Auto-Recognition System Based on Deep Learning

6th Annual 2018 International Conference on Geo-Spatial Knowledge and Intelligence

Shi, Lin^1 ; Li, Zhigang^2 ; Song, Dingli^3

Computer Science Department, North China University of Science and Technology, China^1

Computer Center, TangShan College, China^2

College of Science, North China University of Science and Technology, China^3

关键词: CNN network;    Daily lives;    High-accuracy;    Inter class;    Intra-class variation;    Recognition accuracy;    Recognition systems;    Transfer learning;   

Others  :  https://iopscience.iop.org/article/10.1088/1755-1315/234/1/012088/pdf
DOI  :  10.1088/1755-1315/234/1/012088

来源: IOP

【 摘 要 】

Building a flower auto recognition system with high accuracy is very significant. At the same time, it can bring convenience to our daily life. But Inter-class similarities between different species and the intra-class variation among the same species is a giant challenge needing addressed. Thus, this paper proposes a flower auto-recognition system based on deep learning, we get pictures by mobile smartphone and send the image to the CNN network, which is retrained by transfer learning based on Inception-V3. At last, an experiment was taken to verify the recognition accuracy is higher than other methods.