{"id":23265,"date":"2025-04-16T13:56:00","date_gmt":"2025-04-16T13:56:00","guid":{"rendered":"https:\/\/www.compass-horizon.eu\/?p=23265"},"modified":"2025-11-20T14:26:46","modified_gmt":"2025-11-20T14:26:46","slug":"segmentation-aware-attention-mechanism-for-defect-classification-of-both-virgin-and-recycled-carbon-fiber-fabric-from-composite-2025","status":"publish","type":"post","link":"https:\/\/www.compass-horizon.eu\/?p=23265","title":{"rendered":"Segmentation Aware Attention Mechanism for Defect Classification of both Virgin and Recycled Carbon Fiber Fabric | from COMPOSITE 2025"},"content":{"rendered":"\n<p class=\"wp-block-paragraph\"><a href=\"https:\/\/www.setcor.org\/conferences\/composites-2025\" target=\"_blank\" rel=\"noreferrer noopener\">from COMPOSITE 2025<\/a><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Using neural networks for photometric stereo based surface inspection is fast emerging, especially for carbon fiber matrix (before binding with resins) \/ fabric. <\/p>\n\n\n\n<p class=\"wp-block-paragraph\">However, the non-rigid nature and high reflectivity of the carbon fiber material makes them very difficult to perfrom robust digital image based quality inspection.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">To overcome this issue:<br>1) a dataset was collected with photometric stereo feature modalities and open sourced<br>2) studied the classification performance and the dataset <br>3) propose a segmentation supervised multi-head defect lassification model.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Several standard vision classifier models are retrainded on the created dataset to benchmark the permormance of our model. <\/p>\n\n\n\n<p class=\"wp-block-paragraph\">This paper demonstrates that a segmentation supervised multi-head neural network outperforms the benchmark.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">The realized classifier model achieves over 30% higher accuracy compared to standard CNNs and transformer models. The dataset for classification and its parser its avalaible at <a href=\"https:\/\/zenodo.org\/records\/11203952\" target=\"_blank\" rel=\"noreferrer noopener\">this link<\/a>.<\/p>\n\n\n\n<div class=\"wp-block-buttons is-layout-flex wp-block-buttons-is-layout-flex\">\n<div class=\"wp-block-button\"><a class=\"wp-block-button__link has-background wp-element-button\" href=\"https:\/\/www.compass-horizon.eu\/wp-content\/uploads\/2025\/11\/Segmentation-Aware-Attention-Mechanism-for-Defect-Classification-of-both-Virgin-and-Recycled-Carbon-Fiber-Fabric.pdf\" style=\"background:linear-gradient(135deg,rgb(2,3,129) 100%,rgb(40,116,252) 100%)\" target=\"_blank\" rel=\"noreferrer noopener\">Read the paper<\/a><\/div>\n<\/div>\n\n\n\n<figure class=\"wp-block-image size-large\"><a href=\"https:\/\/www.setcor.org\/conferences\/composites-2025\" target=\"_blank\" rel=\" noreferrer noopener\"><img fetchpriority=\"high\" decoding=\"async\" width=\"1024\" height=\"435\" src=\"https:\/\/www.compass-horizon.eu\/wp-content\/uploads\/2025\/11\/Composite2025-1024x435.jpg\" alt=\"\" class=\"wp-image-23266\" srcset=\"https:\/\/www.compass-horizon.eu\/wp-content\/uploads\/2025\/11\/Composite2025-1024x435.jpg 1024w, https:\/\/www.compass-horizon.eu\/wp-content\/uploads\/2025\/11\/Composite2025-300x127.jpg 300w, https:\/\/www.compass-horizon.eu\/wp-content\/uploads\/2025\/11\/Composite2025-768x326.jpg 768w, https:\/\/www.compass-horizon.eu\/wp-content\/uploads\/2025\/11\/Composite2025-1536x652.jpg 1536w, https:\/\/www.compass-horizon.eu\/wp-content\/uploads\/2025\/11\/Composite2025-2048x869.jpg 2048w, https:\/\/www.compass-horizon.eu\/wp-content\/uploads\/2025\/11\/Composite2025-710x301.jpg 710w\" sizes=\"(max-width: 1024px) 100vw, 1024px\" \/><\/a><\/figure>\n\n\n\n<p class=\"wp-block-paragraph\"><\/p>\n","protected":false},"excerpt":{"rendered":"<p>from COMPOSITE 2025 Using neural networks for photometric stereo based surface inspection is fast emerging, especially for carbon fiber matrix (before binding with resins) \/ fabric. However, the non-rigid nature and high reflectivity of the carbon fiber material makes them very difficult to perfrom robust digital image based quality inspection. To overcome this issue:1) a [&hellip;]<\/p>\n","protected":false},"author":2,"featured_media":23270,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1,34],"tags":[],"class_list":["post-23265","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-news","category-papers-and-publications"],"_links":{"self":[{"href":"https:\/\/www.compass-horizon.eu\/index.php?rest_route=\/wp\/v2\/posts\/23265","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.compass-horizon.eu\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.compass-horizon.eu\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.compass-horizon.eu\/index.php?rest_route=\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.compass-horizon.eu\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=23265"}],"version-history":[{"count":4,"href":"https:\/\/www.compass-horizon.eu\/index.php?rest_route=\/wp\/v2\/posts\/23265\/revisions"}],"predecessor-version":[{"id":23275,"href":"https:\/\/www.compass-horizon.eu\/index.php?rest_route=\/wp\/v2\/posts\/23265\/revisions\/23275"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.compass-horizon.eu\/index.php?rest_route=\/wp\/v2\/media\/23270"}],"wp:attachment":[{"href":"https:\/\/www.compass-horizon.eu\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=23265"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.compass-horizon.eu\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=23265"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.compass-horizon.eu\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=23265"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}