Worm-like image descriptor for signboard classification

dc.contributor.author	Samarin A.
dc.contributor.author	Malykh V.
dc.date.accessioned	2021-02-25T06:51:33Z
dc.date.available	2021-02-25T06:51:33Z
dc.date.issued	2020
dc.identifier.issn	1613-0073
dc.identifier.uri	https://dspace.kpfu.ru/xmlui/handle/net/161134
dc.description.abstract	© 2020 for this paper by its authors. We introduce a special image descriptor that is well suited for classification of images containing various inscriptions. In order to demonstrate effectiveness of the proposed solution we provide evaluation of a system based on the introduced descriptor on commercial building facade photographs grouping problem according to the type of services provided. Our system achieved state of the art performance (0.28 in averaged F1) over classical CNN-based methods and a composite baseline.
dc.relation.ispartofseries	CEUR Workshop Proceedings
dc.subject	Image classification
dc.subject	Image descriptor
dc.subject	Signboard recognition
dc.subject	Visual characteristics
dc.title	Worm-like image descriptor for signboard classification
dc.type	Conference Paper
dc.relation.ispartofseries-volume	2691
dc.collection	Публикации сотрудников КФУ
dc.source.id	SCOPUS16130073-2020-2691-SID85092459926

Файлы в этом документе

Имя: SCOPUS16130073-20 ...

Размер: 48.10Kb

Формат: PDF

Публикации сотрудников КФУ Scopus [24551]
Коллекция содержит публикации сотрудников Казанского федерального (до 2010 года Казанского государственного) университета, проиндексированные в БД Scopus, начиная с 1970г.