Surface Defect Detection of Chinese Dates Based on Machine Vision

Abstract:

In order to implement the accuracy and robust of Chinese dates surface defect detection based on machine vision techniques on line, the method of detection for Chinese dates was studied. The Chinese date is segmented from the background in RGB color space by analyzing respectively the histogram of R, G and B channel to make comparing among them and find an optimal one, resulting in good contrast between Chinese date and background in G channel. The brightness of the damaged area edge changed clearly on the whole Chinese dates area according to the gray image of R, G and B channel, especially in G channel. It shows the gray value of the defect area breaking obviously. So the damaged area could be detected by edge detect, through image thinning the defect edge was extracted. Furthermore, the geometry parameters of defect edge were calculated, these parameters could used to distinguish the defect area with the fruit area and the degree of the defect area. Experiments result proved the methods is effective to detect defect area of Chinese date.

• Periodical: Advanced Materials Research (Volumes 403-408)
• Pages: 1356-1359
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.403-408.1356
• Online since: November 2011
• Authors: Fu Juan Wang, Yong Qiang Dong
• Keywords: Chinese Dates, Defect Detect, Machine Vision, Quality Inspection

References

[1] Davenel A C, Guizard T, Labarre Sevila. Automatic detection of surface defects on fruit by using a vision system[J]. Journal of Agricultural Engineering Research, 1988, 41(1): 1~9.

DOI: 10.1016/0021-8634(88)90198-9

[2] Rehkugler G, Throop J. Image processing algorithm for apple defect detection [J]. Transactions of the ASAE, 1989, 32(1): 267~272.

DOI: 10.13031/2013.30994

[3] He Dongjian, Geng Nan, Dang Gerong. Accurate Measurement of Defect Edge by the Active Contour Models [J]. Transactions of the CSAE, 2001, 17(5): 159~162.

[4] He Dongjian, Yang Qing, Xue Shaoping. Mensuration Studay of furit surface defect based on computer vision[J]. Transactions of the ASAE, 1997, 13(4): 156~160.

[5] Leemans V, Destain M. A real-time grading method of apple base on features extracted from defects[J]. Journal of food engineering, 2004, 61: 83-89.

DOI: 10.1016/s0260-8774(03)00189-4

[6] Zhang Wenying, Ying Yibin. Study on detecting methods for apple stem and defected surface with computer vision[J]. Journal of Zhejiang University, 2001, 27(5): 583~586.

[7] Zhang Yuanpeng, Dong Hai, Zhou Wenling. Basis of Image Processing by Computer[M]. Beijing: Beijing University Press, 1996. 9.

[8] Zou Xiaobo, Zhao Jiewen, Li Yanxiao. Apple color grading based on organization feature parameters[J]. Pattern Recognition Letters, 2007, 28(15): 2 046~2 053.

DOI: 10.1016/j.patrec.2007.06.001