Yazar "Yildiz, Burak" seçeneğine göre listele

Listeleniyor 1 - 3 / 3
  • Küçük Resim Yok
    Öğe
    Distinctive interest point selection for efficient near-duplicate image retrieval
    (Institute of Electrical and Electronics Engineers Inc., 2016) Yildiz, Burak; Demirci, M. Fatih
    Distinctive subset of the interest points creation for near-duplicate image retrieval is significant in two terms. The former is that the query time decreases reasonably. The latter is that using the distinctive subsets performs better than the ordinary subsets. In this paper, we focus on the creation of such subsets for effective near-duplicate retrieval and propose a novel interest point selection method. In this method, the distinctive subset is created with a ranking according to a density map calculated from the interest points. We examined a number of experiments to show the performance of the proposed method and we got a convincing result of 95.46% recall while the precision is still 96.04%. © 2016 Elsevier B.V., All rights reserved.
  • Küçük Resim Yok
    Öğe
    Distinctive Interest Point Selection for Efficient Near-duplicate Image Retrieval
    (Ieee, 2016) Yildiz, Burak; Demirci, M. Fatih
    Distinctive subset of the interest points creation for near-duplicate image retrieval is significant in two terms. The former is that the query time decreases reasonably. The latter is that using the distinctive subsets performs better than the ordinary subsets. In this paper, we focus on the creation of such subsets for effective near-duplicate retrieval and propose a novel interest point selection method. In this method, the distinctive subset is created with a ranking according to a density map calculated from the interest points. We examined a number of experiments to show the performance of the proposed method and we got a convincing result of 95.46% recall while the precision is still 96.04%.
  • Küçük Resim Yok
    Öğe
    Name spell-check framework for social networks
    (Tubitak Scientific & Technological Research Council Turkey, 2016) Yildiz, Burak; Emekci, Fatih
    The problem of finding similar strings is very important in most real life applications including spell-checking, data cleaning, next generation sequencing, and alignment. In order to query and manage string data online, scalable algorithms and frameworks are essential. Scalable frameworks and algorithms have been introduced in the past few years. However, these frameworks mainly deal with caching and querying structured data. They do not deal with fuzzy queries, where we need to search for an approximate string. In this paper, we propose an edit distance aware filtering algorithm for all kinds of approximate string search problems. We also propose a novel name spell-check engine mainly for social networks. Our experiments show that our edit distance aware filtering mechanism alone improves the query processing time and throughput by almost 30%. Additionally, our name spell-check engine improved the name spell-check response time and throughput almost 10 times by using our filtering scheme and some domain specific observations.