DSpace Repository

A Hybrid Framework for Matching Printing Design Files to Product Photos

Show simple item record

dc.contributor.author Kaplan, Alper
dc.contributor.author Akagündüz, Erdem
dc.date.accessioned 2021-06-11T10:36:11Z
dc.date.available 2021-06-11T10:36:11Z
dc.date.issued 2020
dc.identifier.citation Kaplan, Alper; Akagündüz, Erdem (2020). "A Hybrid Framework for Matching Printing Design Files to Product Photos", Balkan Journal of Electrical and Computer Engineering, Vol. 8, No. 2, pp. 170-180. tr_TR
dc.identifier.issn 2147-284X
dc.identifier.uri http://hdl.handle.net/20.500.12416/4782
dc.description.abstract We propose a real-time image matching framework, which is hybrid in the sense that it uses both hand-crafted features and deep features obtained from a well-tuned deep convolutional network. The matching problem, which we concentrate on, is specific to a certain application, that is, printing design to product photo matching. Printing designs are any kind of template image files, created using a design tool, thus are perfect image signals. However, photographs of a printed product suffer many unwanted effects, such as uncontrolled shooting angle, uncontrolled illumination, occlusions, printing deficiencies in color, camera noise, optic blur, et cetera. For this purpose, we create an image set that includes printing design and corresponding product photo pairs with collaboration of an actual printing facility. Using this image set, we benchmark various hand-crafted and deep features for matching performance and propose a framework in which deep learning is utilized with highest contribution, but without disabling real-time operation using an ordinary desktop computer. tr_TR
dc.language.iso eng tr_TR
dc.relation.isversionof 10.17694/bajece.677326 tr_TR
dc.rights info:eu-repo/semantics/openAccess tr_TR
dc.subject Image Matching tr_TR
dc.subject Hand-Crafted Features tr_TR
dc.subject Deep Features tr_TR
dc.subject Semantic Segmentation tr_TR
dc.subject Product Image Processing tr_TR
dc.title A Hybrid Framework for Matching Printing Design Files to Product Photos tr_TR
dc.type article tr_TR
dc.relation.journal Balkan Journal of Electrical and Computer Engineering tr_TR
dc.contributor.authorID 233834 tr_TR
dc.identifier.volume 8 tr_TR
dc.identifier.issue 2 tr_TR
dc.identifier.startpage 170 tr_TR
dc.identifier.endpage 180 tr_TR
dc.contributor.department Çankaya Üniversitesi, Mühendislik Fakültesi, Elektrik-Elektronik Mühendisliği Bölümü tr_TR


Files in this item

This item appears in the following Collection(s)

Show simple item record