Eggshell crack detection based on acoustic response and support vector data description algorithm

A system based on acoustic resonance and combined with pattern recognition was attempted to discriminate cracks in eggshell. Support vector data description (SVDD) was employed to solve the classification problem due to the imbalanced number of training samples. The frequency band was between 1,000 and 8,000 Hz. Recursive least squares adaptive filter was used to process the response signal. Signal-to-noise ratio of acoustic impulse response was remarkably enhanced. Five characteristics descriptors were extracted from response frequency signals, and some parameters were optimized in building model. Experiment results showed that in the same condition SVDD got better performance than conventional classification methods. The performance of SVDD model was achieved with crack detection level of 90% and a false rejection level of 10% in the prediction set. Based on the results, it can be concluded that the acoustic resonance system combined with SVDD has significant potential in the detection of cracked eggs.

[1]  Quansheng Chen,et al.  Feasibility study on identification of green, black and Oolong teas using near-infrared reflectance spectroscopy based on support vector machine (SVM). , 2007, Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy.

[2]  Licheng Jiao,et al.  Artificial immune kernel clustering network for unsupervised image segmentation , 2008 .

[3]  Robert P. W. Duin,et al.  Support vector domain description , 1999, Pattern Recognit. Lett..

[4]  Pawel Podsiadlo,et al.  Fast classification of engineering surfaces without surface parameters , 2006 .

[5]  Giles M. Foody,et al.  Mapping specific habitats from remotely sensed imagery: Support vector machine and support vector data description based classification of coastal saltmarsh habitats , 2007, Ecol. Informatics.

[6]  Hyun-Woo Cho,et al.  Data description and noise filtering based detection with its application and performance comparison , 2009, Expert Syst. Appl..

[7]  J. De Baerdemaeker,et al.  Experimental analysis of the dynamic, mechanical behaviour of a chicken egg , 2003 .

[8]  Lei Guo,et al.  Robust bearing performance degradation assessment method based on improved wavelet packet–support vector data description , 2009 .

[9]  H.-K. Cho,et al.  DETECTION OF SURFACE CRACKS IN SHELL EGGS BY ACOUSTIC IMPULSE METHOD , 2000 .

[10]  Xin Wang,et al.  Performance analysis of RLS linearly constrained constant modulus algorithm for multiuser detection , 2009, Signal Process..

[11]  Zhengding Qiu,et al.  The effect of imbalanced data sets on LDA: A theoretical and empirical analysis , 2007, Pattern Recognit..

[12]  Yi-Hung Liu,et al.  Automatic target defect identification for TFT-LCD array process inspection using kernel FCM-based fuzzy SVDD ensemble , 2009, Expert Syst. Appl..

[13]  Anders Høst-Madsen.  Joint delay and impulse response estimation using sliding RLS filters , 2000, Signal Process..

[14]  Lu Wencong,et al.  Support vector regression applied to materials optimization of sialon ceramics , 2006 .

[15]  Victor I. Djigan,et al.  Multichannel parallelizable sliding window RLS and fast RLS algorithms with linear constraints , 2006, Signal Process..

[16]  J. De Baerdemaeker,et al.  Eggshell Crack Detection based on Acoustic Resonance Frequency Analysis , 2000 .

[17]  Giles M. Foody,et al.  Training set size requirements for the classification of a specific class , 2006 .

[18]  L. Duponchel,et al.  Support vector machines (SVM) in near infrared (NIR) spectroscopy: Focus on parameters optimization and model interpretation , 2009 .

[19]  Jun Wang,et al.  Eggshell crack detection by dynamic frequency analysis , 2005 .

[20]  Jun Wang,et al.  Fabric defect detection based on multiple fractal features and support vector data description , 2009, Eng. Appl. Artif. Intell..

[21]  Robert P. W. Duin,et al.  Support Vector Data Description , 2004, Machine Learning.

[22]  Sang-Woong Lee,et al.  Low resolution face recognition based on support vector data description , 2006, Pattern Recognit..

[23]  T. Adalı,et al.  On steady-state performance of the fixed-point RLS algorithm , 1999 .

[24]  V. M. Puri,et al.  Measurement of Eggshell Thermal-mechanical Properties , 1995 .

[25]  Jue Wang,et al.  A new maximum margin algorithm for one-class problems and its boosting implementation , 2005, Pattern Recognit..

[26]  J.S.H. Tsai,et al.  A boundary method for outlier detection based on support vector domain description , 2009, Pattern Recognit..

[27]  Robert P. W. Duin,et al.  Uniform Object Generation for Optimizing One-class Classifiers , 2002, J. Mach. Learn. Res..

[28]  Bart De Ketelaere,et al.  Noise cancellation in on-line acoustic impulse response measurements for the quality assessment of consumption eggs , 2004, Math. Comput. Simul..

[29]  J. Geoffrey Chase,et al.  Efficient structural health monitoring for a benchmark structure using adaptive RLS filters , 2005 .