Comparing Threshold-Selection Methods for Image Segmentation: Application to Defect Detection in Automated Visual Inspection Systems

详细信息    查看全文

• 关键词：Automated thresholding ; Otsu ; Valley ; Emphasis ; Maximum Similarity Thresholding ; Kittler ; Illingworth
• 刊名：Lecture Notes in Computer Science
• 出版年：2016
• 出版时间：2016
• 年：2016
• 卷：9703
• 期：1
• 页码：33-43
• 全文大小：710 KB
• 参考文献：1.Otsu, N.: A threshold selection method from gray-level histograms. IEEE Trans. Syst. Man Cybern. 9(1), 62–66 (1979)MathSciNet CrossRef
  2.Hui-Fuang, Ng: Automatic thresholding for defect detection. Pattern Recogn. Lett. 27, 1644–1649 (2006)CrossRef
  3.Fan, J., Lei, B.: A modified valley-emphasis method for automatic thresholding. Pattern Recogn. Lett. 33, 703–708 (2012)CrossRef
  4.Kittler, J., Illingworth, J.: Minimum error thresholding. Pattern Recogn. 19, 41–47 (1986)CrossRef
  5.Yaobin, Z., Shuifa, S., Fangmin, D.: Maximum similarity thresholding. Digital Sig. Process. 28, 120–135 (2014)CrossRef
  6.Crum, W., Camara, O., Hill, D.: Generalized overlap measures for evaluation and validation in medical image analysis. IEEE Trans. Med. Imaging 25(11), 1451–1461 (2006)CrossRef
  7.Duda, R., Hart, P.: Pattern Classification and Scene Analysis. Wiley, New York (1973)MATH
  8.Rodgers, J., Nicewander, W.: Thirteen ways to look at the correlation coefficient. Am. Stat. 42, 59–66 (1988)CrossRef
  9.Christian, D., Bernd, A., Carsten, G.: Industrial Image Processing. Springer, Heidelberg (2013)
  10.Davies, D.: Machine Vision – Theory, Algorithms, Practicalities. Elsevier, Philadelphia (2005)
  11.Ridler, T., Calvard, S.: Picture thresholding using an iterative selection method. IEEE Trans. Syst. Man Cybern. 8, 630–632 (1978)CrossRef
  12.Point Grey: Register Reference for Point Grey Digital Cameras (2015). www.​ptgrey.​com
  
• 作者单位：Rafael López-Leyva (18)
  Alfonso Rojas-Domínguez (18)
  Juan Pablo Flores-Mendoza (18)
  Miguel Ángel Casillas-Araiza (18)
  Raúl Santiago-Montero (18)
  
  18. Tecnológico Nacional de México - Instituto Tecnológico de León, Av. Tecnológico S/N - Frac. Industrial Julián de Obregón, 37290, Leóng Gto., Mexico
  
• 丛书名：Pattern Recognition
• ISBN：978-3-319-39393-3
• 刊物类别：Computer Science
• 刊物主题：Artificial Intelligence and Robotics
  Computer Communication Networks
  Software Engineering
  Data Encryption
  Database Management
  Computation by Abstract Devices
  Algorithm Analysis and Problem Complexity
  
• 出版者：Springer Berlin / Heidelberg
• ISSN：1611-3349
• 卷排序：9703

文摘

Automatic detection of defects on the surface of products or raw material is an important task in the field of automated visual inspection. Thresholding is a method for image segmentation that is often used for the detection of said defects. Several methods to select the optimal thresholding values automatically on a per-image base have been described in the literature. Some of these are particularly designed to deal with mostly homogeneous images such as those of product surfaces with some defects, but have not been tested sufficiently and not in the context of automated visual inspection. In this work we present a comparison based on such experimental conditions by means of an automated visual inspection station and a set of images specially acquired for this purpose. The methods that were compared are: the Otsu’s method, the Valley-Emphasis method, the Valley Emphasis with Neighborhood method, the Kittler-Illingworth’s method, and the Maximum Similarity Thresholding method. The highest performance, with a statistically significant difference, was obtained by Maximum Similarity Thresholding.