Eggshell crack detection based on acoustic impulse response and supervised pattern recognition

Abstract

Lin H., Zhao J., Chen Q., Cai J., Zhou P. (2009): Eggshell crack detection based on acoustic impulse response and supervised pattern recognition. Czech J. Food Sci., 27: 393-402.A system based on acoustic resonance was developed for eggshell crack detection. It was achieved by the analysis of the measured frequency response of eggshell excited with a light mechanism. The response signal was processed by recursive least squares adaptive filter, which resulted in the signal-to-noise ratio of the acoustic impulse response reing remarkably enhanced. Five features variables were exacted from the response frequency signals. To develop a robust discrimination model, three pattern recognition algorithms (i.e. K-nearest neighbours, artificial neural network, and support vector machine) were examined comparatively in this work. Some parameters of the model were optimised by cross-validation in the building model. The experimental results showed that the performance of the support vector machine model is the best in comparison to k-nearest neighbours and artificial neural network models. The optimal support vector machine model was obtained with the identification rates of 95.1% in the calibration set, and 97.1% in the prediction set, respectively. Based on the results, it was concluded that the acoustic resonance system combined with the supervised pattern recognition has a significant potential for the cracked eggs detection.

Identification of eggshell crack using multiple vibration sensors and correlative information analysis

“…According to the related references (Lin et al, , 2009b; Sun, Bi, et al, ; Wang & Jiang, ) and analyzing vibration response signals of a large number of intact and cracked eggs from preliminary experiment, ten characteristics of signals were extracted. These characteristics were average; range (maximum value of response signal minus to minimum value of response signal); standard deviation; maximum values and minimum values of response signals; sum of the first ten maximum values of response signals; the maximum and standard deviation of first‐order derivative of response signals; the maximum and minimum of second‐order derivative of response signals; and coefficient of variation.…”

“…Detection of eggshell crack based on vibration response signal of three vibration sensors combined with correlative information analysis was attempted in this study. The possibility of detecting crack on eggs by analyzing of the dynamical frequency response of eggshells has been proved (de Ketelaere et al, 2000;Lin et al 2009b). However, the response signal of egg was greatly affected by the distance of crack region to impacting location.…”

“…Nedomová, Trnka, Dvořáková, Buchar, and Severa ()) and NeDomová, Severa, and Buchar () reported that the acoustic response signals of eggs were affected by impacting locations and force. Lin, Zhao, Chen, Cai, and Zhou (, 2009b) also developed an experimental system combined with supervised recognition pattern to discriminate intact and cracked eggs, and employed support vector data description to solve the problem of imbalanced training numbers. Principal component analysis (PCA) was used to extract features from response signals, and linear discriminant analysis (LDA) was adopted to discriminate cracked eggs.…”

Study on Quality Response to Environmental Factors and Geographical Traceability of Wild Gentiana rigescens Franch

“…The assign of training and test samples was same as the PLS-DA model. In addition, Radial Basis Function (RBF) was preferred to build SVM model for handling the nonlinear and linear relationships between spectra data (Zhao et al, 2009). To attain a good classification result, penalty parameter c and kernel parameter g were used to optimize the SVM model.…”

A Microcontroller-Based Egg Candling System

“…Bamiles et al [4] successfully used a combination of two light wavelengths (577 and 610 nm) to determine the fertility of an egg after 4.5 to 5 days of development. Other reported methods for determining egg fertility include machine vision and LS estimation [5], magnetic resonance imaging [6], acoustic resonant analysis [7] high frequency ultrasound imaging [8], hyperspectral imaging [9], [10] and acoustic impulse response and supervised pattern recognition [11].…”