Abstract
This paper proposed a method of meat recognition method based on the artificial neural network of wavelet denoising. In this study, visible reflected spectra (from 380nm to 780nm) of beef and pork with different freshness were measured with fiber sensor spectrometer. The wavelet multi-resolution analysis was employed and the ideal way of decomposing layers was selected to eliminate the burr noise or abnormal data caused by absorption and scattering spectra signals in optical fiber. Then a kind of with a double-hidden layer was applied to analyze meat spectral reflectance data, and the back propagation-artificial neural network (BP-ANN) was trained by Polak–Ribiere conjugate gradient learning algorithm. The experimental results show that the method can analyse the complex spectrum signals and achieve a good identification on the species and freshness of meat.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Optik - International Journal for Light and Electron Optics
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
