Efficient near-duplicate image detection with created feature subset Olusturulan Öznitelik Alt Kümesiyle Verimli Neredeyse Özdes Görüntü Tespiti

Yildiz B., Demirci M. F.

24th Signal Processing and Communication Application Conference, SIU 2016, Zonguldak, Turkey, 16 - 19 May 2016, pp.1901-1904, (Full Text) identifier

  • Publication Type: Conference Paper / Full Text
  • Doi Number: 10.1109/siu.2016.7496136
  • City: Zonguldak
  • Country: Turkey
  • Page Numbers: pp.1901-1904
  • Keywords: density map creation, interest point selection, near-duplicate image detection, near-duplicate image retrieval
  • Ankara Yıldırım Beyazıt University Affiliated: No

Abstract

© 2016 IEEE.The creation of distinctive subset of the interest points for near-duplicate image detection is significant in two terms. The former is that the query time decreases reasonably. The latter is that using the distinctive subset of the interest points for near-duplicate detection performs better than the ordinary subsets. In this paper, we propose a novel interest point selection method. Such a method, the distinctive subset is created with a density map which is calculated from the interest points to rank them. We examined some experiments to show the performance of the proposed method and we get a performance of 95.46% recall while the precision is 96.04%.