Training Image Synthesis for Shelf Item Detection reflecting Alignments of Items in Real Image Dataset

dc.contributor.authorTomokazu, Kaneko
dc.contributor.authorSakai, Ryosuke
dc.contributor.authorShiraishi, Soma
dc.contributor.editorSkala, Václav
dc.date.accessioned2023-10-17T13:45:19Z
dc.date.available2023-10-17T13:45:19Z
dc.date.issued2023
dc.description.abstract-translatedWe propose a novel cut-and-paste approach to synthesize a training dataset for shelf item detection, reflecting the alignments of items in the real image dataset. The conventional cut-and-paste approach synthesizes large numbers of training images by pasting foregrounds on background images and is effective for training object detection. However, the previous method pastes foregrounds on random positions of the background, so the alignment of items on shelves is not reflected, and unrealistic images are generated. Generating realistic images that reflect actual positional relationships between items is necessary for efficient learning of item detection. The proposed method determines the pasting positions for the foreground images by referring to the alignment of the items in the real image dataset, so it can generate more realistic images that reflect the alignment of the real-world items. Since our method can synthesize more realistic images, the trained models can perform better.en
dc.format9 s.cs
dc.format.mimetypeapplication/pdf
dc.identifier.citationWSCG 2023: full papers proceedings: 1. International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision, p. 81-89.en
dc.identifier.doihttps://www.doi.org/10.24132/CSRN.3301.11
dc.identifier.isbn978-80-86943-32-9
dc.identifier.issn2464–4617 (print)
dc.identifier.issn2464–4625 (CD/DVD)
dc.identifier.urihttp://hdl.handle.net/11025/54413
dc.language.isoenen
dc.publisherVáclav Skala - UNION Agencyen
dc.rights© Václav Skala - UNION Agencyen
dc.rights.accessopenAccessen
dc.subjectdetekce objektucs
dc.subjectsyntéza tréninkových datcs
dc.subjectrozpoznávání maloobchodních položekcs
dc.subjectautomatická anotacecs
dc.subject.translatedobject detectionen
dc.subject.translatedtraining data synthesisen
dc.subject.translatedretail item recognitionen
dc.subject.translatedautomatic annotationen
dc.titleTraining Image Synthesis for Shelf Item Detection reflecting Alignments of Items in Real Image Dataseten
dc.typekonferenční příspěvekcs
dc.typeconferenceObjecten
dc.type.statusPeer-revieweden
dc.type.versionpublishedVersionen

Files

Original bundle
Showing 1 - 1 out of 1 results
No Thumbnail Available
Name:
E43-full.pdf
Size:
3.76 MB
Format:
Adobe Portable Document Format
Description:
Plný text
License bundle
Showing 1 - 1 out of 1 results
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description: