Near-duplicate image recognition

Результат исследований: Материалы для книги/типы отчетовМатериалы для конференции

3 Цитирования (Scopus)

Аннотация

Usage of multi-step segmentation for near-duplicate image recognition is investigated. The search pattern based on the rank distributions of the brightness clusters cardinality is suggested. Experimental results on the near-duplicate image recognition based on the application of the suggested search pattern are given. It is shown that the use of a multi-step segmentation and rank distributions of the brightness clusters cardinality allows to successfully recognize the duplicates, that received by the considerable visual distortion of the original image.

Язык оригиналаАнглийский
Название основной публикацииProceedings of 2014 International Conference on Mechanical Engineering, Automation and Control Systems, MEACS 2014
ИздательInstitute of Electrical and Electronics Engineers Inc.
ISBN (печатное издание)9781479962211
DOI
СостояниеОпубликовано - 15 дек 2014
Событие2014 International Conference on Mechanical Engineering, Automation and Control Systems, MEACS 2014 - Tomsk, Российская Федерация
Продолжительность: 16 окт 201418 окт 2014

Конференция

Конференция2014 International Conference on Mechanical Engineering, Automation and Control Systems, MEACS 2014
СтранаРоссийская Федерация
ГородTomsk
Период16.10.1418.10.14

ASJC Scopus subject areas

  • Mechanical Engineering
  • Electrical and Electronic Engineering
  • Control and Systems Engineering

Fingerprint Подробные сведения о темах исследования «Near-duplicate image recognition». Вместе они формируют уникальный семантический отпечаток (fingerprint).

  • Цитировать

    Nemirovskiy, V. B., & Stoyanov, A. K. (2014). Near-duplicate image recognition. В Proceedings of 2014 International Conference on Mechanical Engineering, Automation and Control Systems, MEACS 2014 [6986916] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/MEACS.2014.6986916