Abstract
This paper proposes a new method to improve the classification accuracy by multiple classes classification using multiple SVM. The proposed approach classifies the true and pseudo defects by adding features to decrease the incorrect classification. This approach consists of two steps. First, the features are extracted from the defect candidate region after extracting the difference between the test image and the reference image. Here, candidate extraction is carefully extracted with high accuracy and the useful combination of features is determined using the feature selection. Second, selected features are learned with multiple SVM and classified into the class. When the result has the multiple same voting counts to the same class, the judgment is treated as the difficult class for the classification. It is shown that the proposed approach gives efficient classification with the higher classification accuracy than the previous approaches through the real experiment.
Access provided by Autonomous University of Puebla. Download to read the full chapter text
Chapter PDF
Similar content being viewed by others
Keywords
References
Tanaka, T., Hotta, S., Iga, T., Nakamura, T.: Automatic Image Filter Creation System: To Use for a Defect Classification System. IEICE Technical Report 106(448), 195–198 (2007)
Rau, H., Wu, C.-H.: Automatic Optical Inspection for Detecting Defects on Printed Circuit Board Inner Layers. The International Journal of Advanced Manufacturing Technology 25(9-10), 940–946 (2005)
Kondo, K., et al.: Defect Classification Using Random Feature Selection and Bagging. The Journal of the Institute of Image Electronics Engineers of Japan 38(1), 9–15 (2009) (in Japanese)
Onishi, H., Sasa, Y., Nagai, K., Tatsumi, S.: A Pattern Defect Inspection Method by Grayscale Image Comparison without Precise Image Alignment. J. IEICE, D-II J86-D-II(11), 1531–1545 (2003)
Maeda, S., Ono, M., Kubota, H., Nakatani, M.: Precise Detection of Short Circuit Defect on TFT Substrate by Infrared Image Matching. J. IEICE D-II J80-D-II(9), 2333–2344 (1997)
Numada, M., Koshimizu, H.: A Method for Detecting Globally Distributed Defects by Using Learning with Mahalanobis Distance. In: ViEW 2007, pp. 9–13 (2007)
Kondo, K., Kikuchi, K., Hotta, S., Shibuya, H., Maeda, S.: Defect Classification Using Random Feature Selection and Bagging. IIEEJ 38(1), 9–15 (2009)
Wakabayashi, T., Tsuruoka, S., Kimura, F., Miyake, Y.: Study on Feature Selection in Handwritten Numeral Recognition. IEICE J78-D-II(11), 1627–1638 (1995)
Ishii, K., Ueda, N., Maeda, E., Murase, Y.: Descriptive Pattern Recognition. Ohmsha (1998)
Amabe, H., Nagao, T.: A Support Vector Machine Approach to Defect Classification by Selecting Image Characteristics. In: FIT 2006, vol. I-033, pp. 79–80 (2006)
Roh, B., Yoon, C., Ryu, Y., Oh, C.: A Neural Network Approach to Defect Classification on Printed Circuit Boards. JSPE 67(10), 1621–1626 (2001)
Iwahori, Y., Futamura, K., Adachi, Y.: Discrimination of True Defect and Indefinite Defect with Visual Inspection Using SVM. In: König, A., Dengel, A., Hinkelmann, K., Kise, K., Howlett, R.J., Jain, L.C. (eds.) KES 2011, Part IV. LNCS, vol. 6884, pp. 117–125. Springer, Heidelberg (2011)
Iwahori, Y., Kumar, D., Nakagawa, T., Bhuyan, M.K.: Improved Defect Classification of Printed Circuit Board Using SVM. In: KES IDT 2012, pp. 1–10 (2012)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer International Publishing Switzerland
About this paper
Cite this paper
Nakagawa, T., Iwahori, Y., Bhuyan, M.K. (2013). Defect Classification of Electronic Board Using Multiple Classifiers and Grid Search of SVM Parameters. In: Lee, R. (eds) Computer and Information Science. Studies in Computational Intelligence, vol 493. Springer, Heidelberg. https://doi.org/10.1007/978-3-319-00804-2_9
Download citation
DOI: https://doi.org/10.1007/978-3-319-00804-2_9
Publisher Name: Springer, Heidelberg
Print ISBN: 978-3-319-00803-5
Online ISBN: 978-3-319-00804-2
eBook Packages: EngineeringEngineering (R0)