Apple NIR Spectral Classification Method

DOI

10.2991/icecee-15.2015.38How to use a DOI?

Keywords

Apple; Near Infrared Spectroscopy; Principal Component Analysis; Fisher Decision Analysis; K- Nearest Neighbor Classification

Abstract

This paper proposed an apple near infrared spectral classification method. Red Fuji apples from Shandong and Shaanxi province , “Huaniu” apples from Gansu province were used as experimental materials. NIR data of three kinds of apples after preprocessing by wavelet soft threshold, was removed the noise and redundancy. Then the method of Principal Component Analysis ( PCA) was used to reduce the dimension, and the Fisher Decision Analysis (FDA) was used for further feature extraction. Finally the K-Nearest Neighbor (KNN) classification was run, and K = 4. Through the experimental comparison, the method can achieve good feature extraction and classification of apples. The correct identification rate reaches above 96%. This method can realize different kinds of apples nondestructively, rapidly and accurately, which provides a new idea for near infrared spectral analysis technology.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Min Li
AU  - Jin Cao
AU  - Linju Lu
PY  - 2015/06
DA  - 2015/06
TI  - Apple NIR Spectral Classification Method
BT  - Proceedings of the 2015 International Conference on Electrical, Computer Engineering and Electronics
PB  - Atlantis Press
SP  - 168
EP  - 171
SN  - 2352-538X
UR  - https://doi.org/10.2991/icecee-15.2015.38
DO  - 10.2991/icecee-15.2015.38
ID  - Li2015/06
ER  -