An Identification Method for Cracked Eggs Based on Image Wavelet Transform and Multi-Features Synthesis

Abstract:

An identification method for cracked eggs by means of the digital image technology was proposed in this paper. Firstly, an ideal machine vision system was built and the images of good eggs and cracked eggs were obtained by CCD camera. Secondly, each image was decomposed on two layers of wavelet, so 6 high-frequency sub-images and 2 low-frequency sub-images were extracted. Then joint probability matrix after wavelet transform had been calculated and 5 parameters for each high-frequency sub-images were extracted, so the total of the joint probability matrix parameters was 30 for 6 high-frequency sub-images. At the same time, 10 wavelet energy parameters were obtained. Thirdly, four main factor component scores were selected from above 40 feature parameters after principal component analysis, which were input to support vector machine. Finally, classification model was built by support vector machine. Experiments show that the proposed method was effective to identify the cracked eggs from good eggs and the identification rate was 93.75%.

• Periodical: Applied Mechanics and Materials (Volume 704)
• Pages: 412-418
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.704.412
• Online since: December 2014
• Authors: Li Rong Xiong, Zhi Hui Zhu
• Keywords: Cracked Eggs, Joint Probability Matrix, Multi-Features Synthesis, Support Vector Machine (SVM), Wavelet Transform (WT)

References

[1] Ketelaere B De, Coueke P, Baerdemaeker J De. Eggshell crack detection based on acoustic resonance frequency analysis. J．Agric．Eng．Res, 2000，76(2): 157-163.

DOI: 10.1006/jaer.2000.0542

[2] Cho H K, W-K Choi, J H Pack. Detection of surface in shell eggs by acoustic impulse method. Transactions of the ASAE, 2000, 43(6): 1921-1926.

DOI: 10.13031/2013.3097

[3] Jenshin L, Lin Y, Hsieh M. An automatic system for eggshell quality monitoring. Transactions of the ASAE, 2001, 44(3): 1323-1328.

[4] Wang J, Jiang R S. Eggshell crack detection by dynamic frequency analysis. European Food Research and Technology, 2005, 221(1-2): 214-220.

DOI: 10.1007/s00217-005-1149-9

[5] Jiang Ruishe, wang Jun, Lu Qiujun, et a1. Eggshe1l crack detection by frequency analysis of dynamic resonance. TransactioI1s of the Chinese S0ciety for Agricu1tural Machinery, 2005, 36(3): 75-78.

[6] Pan Leiqing, Tu Kang, Zhao Li, et a1. Preliminary research of chicken egg crack detection based on acoustic resonance analysis. Transactions of the Chinese Society Agricmtura1 Engineering, 2005, 21(4): 1l-15.

[7] Liu Jianying, Tian Maosheng, Wang Qiaohua, Wen Youxian. Design on Testing and Grading Device of Cracked Egg based on DSP. Transactions of CSAM , 2007, 38(12): 125-128.

[8] Cho H K, Kwon Y. Crack detection in eggs by machine vision. Transactions of the ASAE, 1996, 39(3): 777-784.

[9] Zhou Ping, Liu Jianying, Wang Qiaohua, et a1. Egg image detection method and weight prediction model. Transactions of the Chinese Society for Agricultural Machinery, 2007, 38(11): 80-83.

[10] Liu Peng, Tu Kang Pan Leiqing. Duck Egg's Shell Intensity Model Based on Fusion of Computer Vision and Impact Excitation. Transactions of the Chinese Society of Agricultural Machinery, 2009, 8: 175-180.

[11] Peng Hui, Wen Youxian, Wang Qiaohua, Wang Shucai, Wu Lanlan . Crack Detection in Eggs with Multi-level Wavelet Transform and BP Neural Network. Transactions of the Chinese Society of Agricultural Machinery , 2009, 2：170-174.

[12] Zhang Defeng. Matlab Wavelet Analysis. Machinery Industry Press, 2009, pp.5-90.

[13] Zhang Defeng. Matlab Digital Image Process. Machinery Industry Press, 2009, pp.134-158.

[14] Feng Jianhui, Yang Yujing. Study of texture images extraction based on gray layer cooccurence matrix. Beijing Surveying and Mapping, 2007, 3: 19－21.

[15] Wu Gaohong. Zhang Yujin, Lin Xinggang. Texture segmentation with wavelet transform and feature weighting. Pattern recognition and artificial intelligence, 1999, pp.262-267.

DOI: 10.1109/icip.1999.819630

[16] Yu Jialin, Xiao Zhihong. Applied probability and statistics with SAS . Wuhan University Press, 2006, pp.103-123.

[17] Bai Peng, Zhang Xibing, Zhang bing. Support vector machine theory and engineering application. Xidian University Press, 2008, pp.13-20.

[18] Nello Cristianini，John Shawe-Taylor. An introuduction to support vector machines and other kernel-based learning methos. Bejing: Electronics Industry Press, 2004, p.82－107.

DOI: 10.1017/cbo9780511801389