{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,6,2]],"date-time":"2022-06-02T05:12:57Z","timestamp":1654146777591},"reference-count":12,"publisher":"IGI Global","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014,1,1]]},"abstract":"<p>This paper proposes a new method to improve the classification accuracy by multiple class 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, detect the straight line by Hough Transform to the inspection image and condition is judged with the gradient. More than 80% of AOI images consist of images with the margin line between base part and lead line part which has the same direction. When detected line directions are almost the same directions, shifted image of inspection image is generated and used as the reference image. In case of different directions of detected lines (this case holds for less than 20% of AOI images), reference image is generated manually. After the reference image is prepared, the difference is taken between the inspection image and reference image. This leads to extract the defect candidate region with high accuracy and features are extracted to judge the defect and foreign material. 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.<\/p>","DOI":"10.4018\/ijsi.2014010103","type":"journal-article","created":{"date-parts":[[2014,8,1]],"date-time":"2014-08-01T20:18:05Z","timestamp":1406924285000},"page":"25-36","source":"Crossref","is-referenced-by-count":4,"title":["Reduction of Defect Misclassification of Electronic Board Using Multiple SVM Classifiers"],"prefix":"10.4018","volume":"2","author":[{"given":"Takuya","family":"Nakagawa","sequence":"first","affiliation":[{"name":"Chubu University, Aichi, Japan"}]},{"given":"Yuji","family":"Iwahori","sequence":"additional","affiliation":[{"name":"Chubu University, Aichi, Japan"}]},{"given":"M. K.","family":"Bhuyan","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology Guwahati, Assam, India"}]}],"member":"2432","reference":[{"key":"ijsi.2014010103-0","unstructured":"Amabe, H., & Nagao, T. (2006). A support vector machine approach to defect classification by selecting image characteristics. In Proceedings of the FIT2006 (I-033, pp. 79-80)."},{"key":"ijsi.2014010103-1","author":"K.Ishii","year":"1998","journal-title":"Descriptive pattern recognition"},{"key":"ijsi.2014010103-2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-23866-6_13"},{"key":"ijsi.2014010103-3","first-page":"1","article-title":"Improved defect classification of printed circuit board using SVM.","volume":"2012","author":"Y.Iwahori","year":"2012","journal-title":"Proceedings of the KES IDT"},{"key":"ijsi.2014010103-4","first-page":"9","article-title":"Defect classification using random feature selection and bagging.","volume":"38","author":"K.Kondo","year":"2009","journal-title":"The Journal of the Institute of Image Electronics Engineers of Japan"},{"key":"ijsi.2014010103-5","unstructured":"Maeda, S., Ono, M., Kubota, H., & Nakatani, M. (1997). Precise detection of short circuit defect on TFT substrate by infrared image matching. J. IEICE, D-II, J80-D-II, 9, 2333-2344."},{"key":"ijsi.2014010103-6","first-page":"9","article-title":"A method for detecting globally distributed defects by using learning with mahalanobis distance.","volume":"W2007","author":"M.Numada","year":"2007","journal-title":"Proceedings of the ViE"},{"key":"ijsi.2014010103-7","unstructured":"Onishi, H., Sasa, Y., Nagai, K., & Tatsumi, S. (2003). A pattern defect inspection method by grayscale image comparison without precise image alignment. J. IEICE, D-II, J86-D-II, 11, 1531-1545."},{"key":"ijsi.2014010103-8","doi-asserted-by":"publisher","DOI":"10.1007\/s00170-004-2299-9"},{"issue":"10","key":"ijsi.2014010103-9","first-page":"1621","article-title":"A neural network approach to defect classification on printed circuit boards.","volume":"67","author":"B.Roh","year":"2001","journal-title":"JSPE"},{"issue":"448","key":"ijsi.2014010103-10","first-page":"195","article-title":"Automatic image filter creation system: To use for a defect classification system.","volume":"106","author":"T.Tanaka","year":"2007","journal-title":"IEICE Technical Report"},{"key":"ijsi.2014010103-11","unstructured":"Wakabayashi, T., Tsuruoka, S., Kimura, F., & Miyake, Y. (1995). Study on feature selection in handwritten numeral recognition. IEICE, J78-D-II, 1627-1638."}],"container-title":["International Journal of Software Innovation"],"original-title":[],"language":"ng","link":[{"URL":"https:\/\/www.igi-global.com\/viewtitle.aspx?TitleId=111448","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,2]],"date-time":"2022-06-02T04:34:27Z","timestamp":1654144467000},"score":1,"resource":{"primary":{"URL":"https:\/\/services.igi-global.com\/resolvedoi\/resolve.aspx?doi=10.4018\/ijsi.2014010103"}},"subtitle":[""],"short-title":[],"issued":{"date-parts":[[2014,1,1]]},"references-count":12,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2014,1]]}},"URL":"https:\/\/doi.org\/10.4018\/ijsi.2014010103","relation":{},"ISSN":["2166-7160","2166-7179"],"issn-type":[{"value":"2166-7160","type":"print"},{"value":"2166-7179","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,1,1]]}}}