{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T03:17:06Z","timestamp":1774322226766,"version":"3.50.1"},"reference-count":42,"publisher":"Wiley","issue":"12","license":[{"start":{"date-parts":[[2023,9,21]],"date-time":"2023-09-21T00:00:00Z","timestamp":1695254400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["advanced.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Advanced Intelligent Systems"],"published-print":{"date-parts":[[2023,12]]},"abstract":"<jats:p>To increase the reliability of the printed circuit board (PCB) manufacturing process, automated optical inspection is often employed for soldering defect detection. However, traditional approaches built on handcrafted features, predefined rules, or thresholds are often susceptible to the variation of the acquired images\u2019 quality and give unstable performances. To solve this problem, a deep learning\u2010based soldering defect detection method is developed in this article. Like many real\u2010life deep learning applications, the number of available training samples is often limited. This creates a challenging low\u2010data scenario, as deep learning typically requires massive data to perform well. To address this issue, a multitask learning model is proposed, namely, PCBMTL, that can simultaneously learn the classification and segmentation tasks under low\u2010data regimes. By acquiring the segmentation knowledge, classification performance is substantially improved with few samples. To facilitate the study, a soldering defect image dataset, namely, PCBSPDefect, is built. It focuses on the dual in\u2010line packages (DIP) at the PCB back side, DIP at the PCB front side, and flat flexible cables. Experimental results show that the proposed PCBMTL outperforms the best existing approaches by over 5\u201317% of average accuracy for different datasets.<\/jats:p>","DOI":"10.1002\/aisy.202300364","type":"journal-article","created":{"date-parts":[[2023,9,21]],"date-time":"2023-09-21T23:01:09Z","timestamp":1695337269000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["PCB Soldering Defect Inspection Using Multitask Learning under Low Data Regimes"],"prefix":"10.1002","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8578-0696","authenticated-orcid":false,"given":"Sik-Ho","family":"Tsang","sequence":"first","affiliation":[{"name":"Unit 1212-1213 Hong Kong Science Park  12\/F, Building 19W, Pak Shek Kok, NT Hong Kong China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaoqing","family":"Suo","sequence":"additional","affiliation":[{"name":"Unit 1212-1213 Hong Kong Science Park  12\/F, Building 19W, Pak Shek Kok, NT Hong Kong China"},{"name":"Department of Electrical and Electronic Engineering The Hong Kong Polytechnic University  Hung Hom Hong Kong China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tom Tak-Lam","family":"Chan","sequence":"additional","affiliation":[{"name":"Unit 1212-1213 Hong Kong Science Park  12\/F, Building 19W, Pak Shek Kok, NT Hong Kong China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8493-2240","authenticated-orcid":false,"given":"Huu-Thanh","family":"Nguyen","sequence":"additional","affiliation":[{"name":"Unit 1212-1213 Hong Kong Science Park  12\/F, Building 19W, Pak Shek Kok, NT Hong Kong China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3891-1363","authenticated-orcid":false,"given":"Daniel Pak-Kong","family":"Lun","sequence":"additional","affiliation":[{"name":"Unit 1212-1213 Hong Kong Science Park  12\/F, Building 19W, Pak Shek Kok, NT Hong Kong China"},{"name":"Department of Electrical and Electronic Engineering The Hong Kong Polytechnic University  Hung Hom Hong Kong China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2023,9,21]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/33.56166"},{"key":"e_1_2_9_3_1","unstructured":"Y.Matsuyama T.Honda H.Yamamura H.Sasazawa M.Nomoto T.Ninomiya A.Schick L.Listl P.Kollensperger D.Spriegel P.Mengel R.Schneider inIEEE Workshop on Applications of Computer Vision (WACV) IEEE Sarasota FL1996 pp.116\u2013122."},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCPMT.2018.2864666"},{"key":"e_1_2_9_5_1","doi-asserted-by":"crossref","unstructured":"K.Zhang T.Huang Z.Su T.Guan inIEEE Advanced Information Technology Electronic and Automation Control Conf. (IAEAC) IEEE Chongqing China2021 pp.2413\u20132418.","DOI":"10.1109\/IAEAC50856.2021.9390646"},{"key":"e_1_2_9_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2018.2839614"},{"key":"e_1_2_9_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2006.877265"},{"key":"e_1_2_9_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TEPM.2008.2011813"},{"key":"e_1_2_9_9_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"e_1_2_9_10_1","doi-asserted-by":"crossref","unstructured":"S.Gao H.Zhang H.Mi inIEEE Int. Conf. Signal Information and Data Processing (ICSIDP) IEEE Chongqing China2019 pp.1\u20136.","DOI":"10.1109\/ICSIDP47821.2019.9173443"},{"key":"e_1_2_9_11_1","doi-asserted-by":"crossref","unstructured":"D.Ma X.Lei H.Zhao inInt. Conf. Artificial Intelligence and Advanced Manufacturing (AIAM) Dublin Ireland2019 pp.598\u2013603.","DOI":"10.1109\/AIAM48774.2019.00124"},{"key":"e_1_2_9_12_1","unstructured":"K.Simonyan A.Zisserman inInt. Conf. Learning Representations (ICLR) San Diego CA2015 pp.1\u201314."},{"key":"e_1_2_9_13_1","doi-asserted-by":"crossref","unstructured":"M.Metzner D.Fiebag A.Mayr J.Franke inInt. Electric Drives Production Conf. (EDPC) Esslingen Germany2019 pp.1\u20136.","DOI":"10.1109\/EDPC48408.2019.9011820"},{"key":"e_1_2_9_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/s40747-021-00600-w"},{"key":"e_1_2_9_15_1","unstructured":"O.Ronneberger P.Fischer T.Brox inMedical Image Computing and Computer Assisted Intervention (MICCAI) Munich Germany2015 pp.232\u2013241."},{"key":"e_1_2_9_16_1","doi-asserted-by":"crossref","unstructured":"G.Mahalingam K. M.Gay K.Ricanek inInt. Conf. Machine Vision Applications (MVA) Tokyo Japan2019 pp.1\u20135.","DOI":"10.23919\/MVA.2019.8757928"},{"key":"e_1_2_9_17_1","unstructured":"H.Lu D.Mehta O.Paradis N.Asadizanjani M.Tehranipoor D. L.Woodard Cryptology ePrint Archive2020 paper no. 2020\/366 https:\/\/eprint.iacr.org\/2020\/366."},{"key":"e_1_2_9_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00170-020-05125-z"},{"key":"e_1_2_9_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/s41635-019-00088-4"},{"key":"e_1_2_9_20_1","doi-asserted-by":"crossref","unstructured":"Y.Fridman M.Rusanovsky G.Oren inIEEE Physical Assurance and Inspection of Electronics (PAINE) Virtual IEEE Piscataway NJ2021 pp.1\u20138.","DOI":"10.1109\/PAINE54418.2021.9707699"},{"key":"e_1_2_9_21_1","unstructured":"S.Tang F.He X.Huang J.Yang arXiv Preprint arXiv:1902.06197v1 2019."},{"key":"e_1_2_9_22_1","doi-asserted-by":"publisher","DOI":"10.1049\/joe.2019.1183"},{"key":"e_1_2_9_23_1","doi-asserted-by":"publisher","DOI":"10.1002\/aisy.202200142"},{"key":"e_1_2_9_24_1","doi-asserted-by":"publisher","DOI":"10.1002\/aisy.202200151"},{"key":"e_1_2_9_25_1","doi-asserted-by":"crossref","unstructured":"S.-H.Tsang Z.Suo T. T.-L.Chan H.-T.Nguyen D. P.-K.Lun https:\/\/github.com\/cairs-project-5\/PCBSPDefect(accessed: August 2023).","DOI":"10.1002\/aisy.202300364"},{"key":"e_1_2_9_26_1","first-page":"5094","volume":"69","author":"Khalil K.","year":"2022","journal-title":"IEEE Trans. Circuits Syst. II: Exp. Briefs"},{"key":"e_1_2_9_27_1","doi-asserted-by":"crossref","unstructured":"K.Khalil O.Eldash A.Kumar M.Bayoumi inIEEE Int. Conf. Electronics Circuits and Systems (ICECS) IEEE Bordeaux France2018 pp.745\u2013748.","DOI":"10.1109\/ICECS.2018.8617887"},{"key":"e_1_2_9_28_1","doi-asserted-by":"publisher","DOI":"10.1080\/17686733.2023.2225246"},{"key":"e_1_2_9_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3172902"},{"key":"e_1_2_9_30_1","unstructured":"Y.Ge Y.Zhou J.Yang Y.Zhang F.Xie X.Tang inInt. Conf. Robotics Automation Intelligent Control (ICRAIC) Wuhan China2021 pp.1\u20138."},{"key":"e_1_2_9_31_1","doi-asserted-by":"crossref","unstructured":"A.Caliskan G.Gurkan inInt. Conf. Innovations in Intelligent Systems and Applications (INISTA) Kocaeli Turkey2021 pp.1\u20136.","DOI":"10.1109\/INISTA52262.2021.9548430"},{"key":"e_1_2_9_32_1","doi-asserted-by":"crossref","unstructured":"K.He X.Zhang S.Ren J.Sun inIEEE Computer Vision and Pattern Recognition (CVPR) IEEE Las Vegas NV2016 pp.770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_9_33_1","unstructured":"T.Chen S.Kornblith M.Norouzi G. E.Hinton inInt. Conf. Machine Learning (ICML) Vienna Austria2020 pp.1597\u20131607."},{"key":"e_1_2_9_34_1","unstructured":"J.Deng W.Dong R.Socher L.-J.Li K.Li F.-F.Li inIEEE Computer Vision and Pattern Recognition (CVPR) IEEE Miami FL2009 pp.248\u2013255."},{"key":"e_1_2_9_35_1","unstructured":"G.Ghiasi Y.Cui A.Srinivas R.Qian T.-Y.Lin E. D.Cubuk Q. V.Le B.Zoph inIEEE\/CVF Computer Vision and Pattern Recognition (CVPR) IEEE Nashville TN2021 pp.2917\u20132927."},{"key":"e_1_2_9_36_1","unstructured":"I. J.Goodfellow J.Pouget-Abadie M.Mirza B.Xu D.Warde-Farley S.Ozair A.Courville Y.Bengio inInt. Conf. Neural Information Processing Systems (NIPS) Cambridge MA2014 pp.2672\u20132680."},{"key":"e_1_2_9_37_1","unstructured":"S.Ioffe C.Szegedy inInt. Conf. Machine Learning (ICML) Lille France2015 pp.448\u2013456."},{"key":"e_1_2_9_38_1","unstructured":"V.Nair G. E.Hinton inInt. Conf. Machine Learning (ICML) Haifa Israel2010 pp.807\u2013814."},{"key":"e_1_2_9_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2021.3139904"},{"key":"e_1_2_9_40_1","first-page":"1929","volume":"15","author":"Srivastava N.","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"e_1_2_9_41_1","unstructured":"A.Paszke S.Gross F.Massa A.Lerer J.Bradbury G.Chanan T.Killeen Z.Lin N.Gimelshein L.Antiga A.Desmaison A.K\u00f6pf E.Yang Z.DeVito M.Raison A.Tejani S.Chilamkurthy B.Steiner L.Fang J.Bai S.Chintala inNeural Information Processing Systems (NeurIPS) Vancouver Canada2019 pp.1\u201312."},{"key":"e_1_2_9_42_1","unstructured":"D. P.Kingma J.Ba inInt. Conf. Learning Representations (ICLR) San Diego CA2015 pp.1\u201315."},{"key":"e_1_2_9_43_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101912"}],"container-title":["Advanced Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/advanced.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/aisy.202300364","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T22:41:01Z","timestamp":1759876861000},"score":1,"resource":{"primary":{"URL":"https:\/\/advanced.onlinelibrary.wiley.com\/doi\/10.1002\/aisy.202300364"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,21]]},"references-count":42,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2023,12]]}},"alternative-id":["10.1002\/aisy.202300364"],"URL":"https:\/\/doi.org\/10.1002\/aisy.202300364","archive":["Portico"],"relation":{},"ISSN":["2640-4567","2640-4567"],"issn-type":[{"value":"2640-4567","type":"print"},{"value":"2640-4567","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9,21]]},"assertion":[{"value":"2023-06-27","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-09-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"2300364"}}