Ev ve Ofis taşıma sektöründe lider olmak.Teknolojiyi takip ederek bunu müşteri menuniyeti amacı için kullanmak.Sektörde marka olmak.
İstanbul evden eve nakliyat
Misyonumuz sayesinde edindiğimiz müşteri memnuniyeti ve güven ile müşterilerimizin bizi tavsiye etmelerini sağlamak.
Indexing Probabilistic
Attributes in Image Database
Presented by: Jingchun Liu
ABSTRACT: In this report, we present a hierarchical model
to index and retrieve images in the database, mainly for probabilistic
attributes in the image regions. First we model the pixels
in the image region as a Gaussian distribution, then we construct
the index structure using routine index techniques, such as
B-tree. After we obtain the initial retrieval results given
the query region, we refine the retrieval perforemance by
the real probability distribution of pixels estimated from
Parzen window algorithm, and compare the PDF similarity using
Kullback-Leibler information divergence. By the first step,
we can successfully index the probabilistic attributes and
reduce the searching scope, and by the second step, we can
refine the retrieval results and improve performance.
|