|
ИСТИНА |
Войти в систему Регистрация |
ИСТИНА ИНХС РАН |
||
A Riemanian Approach to Blob Detection in Manifold-Valued Images"/ 3rd conference on Geometricстатья
Информация о цитировании статьи получена из
- Авторы: Shestov Aleksei, Kumskov Mikhail
- Сборник: 3rd conference on Geometric Science of Information - 07 Novembre 2017 - 09 Novembre 2017 Mines ParisTech
- Год издания: 2017
- Место издания: Paris (France)
- Аннотация: Abstract. This paper is devoted to the problem of blob detection in manifold-valued images. Our solution is based on new de nitions of blob response functions. We de ne blob response functions by means of cur- vatures of an image graph, considered as a submanifold. We call the proposed framework the Riemannian blob detection. We prove that our approach can be viewed as a generalization of the grayscale blob detec- tion technique. An expression of the Riemannian blob response functions through image Hessian is derived. We provide experiments for the case of vector-valued images on 2D surfaces: the proposed framework is tested on the task of chemical compounds classi cation.
- Добавил в систему: Кумсков Михаил Иванович
Прикрепленные файлы
| № | Имя | Описание | Имя файла | Размер | Добавлен |
|---|---|---|---|---|---|
| 1. | Полный текст | Shestov-Kumskov-gsi2017_paper_77.pdf | 265,8 КБ | 21 декабря 2017 [kumskov] |