DocumentCode :
1864522
Title :
Research on Marine and Freshwater Fish Identification Model Based on Hyper-spectral Imaging Technology
Author :
Guo Peiyuan ; Fu Yan ; Xiang Lingzi ; Bao Man ; Chen Xinghai
Author_Institution :
Coll. of Comput. & Inf. Eng., Beijing Technol. & Bus. Univ., Beijing, China
Volume :
1
fYear :
2013
fDate :
26-27 Aug. 2013
Firstpage :
369
Lastpage :
372
Abstract :
With the gradually mature of hyper spectral image technology, the application of the meat nondestructive detection and recognition has become one of the current research focuses. This paper for the study of marine and freshwater fish by the pre-processing and feature extraction of the collected spectral curve data, combined with BP network structure and LVQ network structure, a predictive model of hyper spectral image data of marine and freshwater fish has been initially established and finally realized the qualitative analysis and identification of marine and freshwater fish quality.
Keywords :
aquaculture; backpropagation; feature extraction; geophysical image processing; hyperspectral imaging; BP network structure; LVQ network structure; feature extraction; freshwater fish identification model; freshwater fish quality; hyper-spectral imaging technology; marine fish identification model; marine fish quality; meat nondestructive detection; meat nondestructive recognition; predictive model; spectral curve data; Hyperspectral imaging; Imaging; Marine animals; Neurons; Predictive models; Reflectivity; Training; BP network; Hyper-spectral image technology; LVQ network; Marine and Freshwater Fish;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Intelligent Human-Machine Systems and Cybernetics (IHMSC), 2013 5th International Conference on
Conference_Location :
Hangzhou
Print_ISBN :
978-0-7695-5011-4
Type :
conf
DOI :
10.1109/IHMSC.2013.94
Filename :
6643906
Link To Document :
بازگشت