CLASSIFICATION OF CLOSED- AND OPEN-SHELL PISTACHIO NUTS USING VOICE-RECOGNITION TECHNOLOGY

Abstract

An algorithm using speech recognition technology was developed to distinguish pistachio nuts with closed shellsfrom those with open shells. It was observed that upon impact with a steel plate, nuts with closed shells emit different soundsthan nuts with open shells. Features extracted from the sound signals consisted of mel-cepstrum coefficients and eigenvaluesobtained from the principle component analysis (PCA) of the autocorrelation matrix of the sound signals. Classification ofa sound signal was performed by linearly combining the mel-cepstrum and PCA feature vectors. An important property ofthe algorithm is that it is easily trainable, as are most speech-recognition algorithms. During the training phase, sounds ofnuts with closed shells and with open shells were used to obtain a representative vector of each class. During the recognitionphase, the feature vector from the sample under question was compared with representative vectors. The classification accuracyof closed-shell nuts was more than 99% on the validation set, which did not include the training set.