Title :
A signal representation approach for discrimination between full and empty hazelnuts
Author :
Onaran, Ibrahim ; Ince, Nuri F. ; Tewfik, Ahmed H. ; Cetin, A. Enis
Author_Institution :
Dept. of Electr. & Electron. Eng., Univ. of Bilkent, Turkey
Abstract :
We apply a sparse signal representation approach to impact acoustic signals to discriminate between empty and full hazelnuts. The impact acoustic signals are recorded by dropping the hazelnut shells on a metal plate. The impact signal is then approximated within a given error limit by choosing codevectors from a special dictionary. This dictionary was generated from sub-dictionaries that are individually generated for the impact signals corresponding to empty and full hazelnut. The number of codevectors selected from each sub-dictionary and the approximation error within initial codevectors are used as classification features and fed to a Linear Discriminant Analysis (LDA). We also compare this algorithm with a baseline approach. This baseline approach uses features which describe the time and frequency characteristics of the given signal that were previously used for empty and full hazelnut separation. Classification accuracies of 98.3% and 96.8% were achieved by the proposed approach and base algorithm respectively. The results we obtained show that sparse signal representation strategy can be used as an alternative classification method for undeveloped hazelnut separation with higher accuracies.
Keywords :
acoustic signal detection; approximation theory; principal component analysis; signal classification; signal representation; LDA; acoustic signals; approximation error; classification features; codevectors; frequency characteristics; hazelnut separation; hazelnut shells; impact signal; linear discriminant analysis; metal plate; sparse signal representation; special dictionary; time characteristics; Approximation error; Decision support systems; Europe; Iron; Signal processing;
Conference_Titel :
Signal Processing Conference, 2007 15th European
Conference_Location :
Poznan
Print_ISBN :
978-839-2134-04-6