{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/online-pcb-defect-detector-on-a-new-pcb","title":"Online PCB Defect Detector On A New PCB Defect Dataset","arxiv_id":"1902.06197","date":"2019-02-17","proceeding":null,"authors":["Sanli Tang","Fan He","Xiaolin Huang","Jie Yang"],"abstract":"Previous works for PCB defect detection based on image difference and image\nprocessing techniques have already achieved promising performance. However,\nthey sometimes fall short because of the unaccounted defect patterns or\nover-sensitivity about some hyper-parameters. In this work, we design a deep\nmodel that accurately detects PCB defects from an input pair of a detect-free\ntemplate and a defective tested image. A novel group pyramid pooling module is\nproposed to efficiently extract features of a large range of resolutions, which\nare merged by group to predict PCB defect of corresponding scales. To train the\ndeep model, a dataset is established, namely DeepPCB, which contains 1,500\nimage pairs with annotations including positions of 6 common types of PCB\ndefects. Experiment results validate the effectiveness and efficiency of the\nproposed model by achieving $98.6\\%$ mAP @ 62 FPS on DeepPCB dataset. This\ndataset is now available at: https://github.com/tangsanli5201/DeepPCB.","url_abs":"http://arxiv.org/abs/1902.06197v1","url_pdf":"http://arxiv.org/pdf/1902.06197v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"online-pcb-defect-detector-on-a-new-pcb","repo_url":"https://github.com/tangsanli5201/DeepPCB","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"defect-detection","task_name":"Defect Detection"}],"methods":[{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"pcb","method_name":"PCB"},{"method_slug":"pyramid-pooling-module","method_name":"Pyramid Pooling Module"},{"method_slug":"relu","method_name":"ReLU"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1902.06197","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}