| KRATKA VSEBINA | Ob pojavu znatnega števila velikih slikovnih podatkovnih zbirk, v katerih so bile slike večinoma opisane s tekstovnimi deskriptorji, se je zaradi nepopolnosti tovrstnega načina opisovanja sčasoma pojavila potreba po drugačnem pristopu do indeksiranja slik in poizvedovanja po njih. Alternativa tekstovnim sistemom poizvedovanja po slikah je poizvedovanje po slikah na podlagi vsebine. Slike so indeksirane na osnovi svoje dejanske vsebine in značilnice, kot so barva, tekstura in oblika so izražene s številčnimi vrednostmi. V procesu poizvedovanja sistemizračuna vrednosti značilnic za podano sliko na isti način, kot so izračunane vrednosti za slike, shranjene v zbirki, in opravi primerjavo. Takšni sistemi so znani pod imenom CBIR (content-based image retrieval) sistemi. V delu predstavimo osnovne karakteristike CBIR sistemov, prosto dostopnih prek svetovnega spleta, in jih primerjamo glede na razvojno okolje, v katerih so nastali, značilnicah, ki jih uporabljajo za opisovanjevsebine slik, in zmožnostjo uporabniškega vmesnika, ki ga sistem ponuja. //With development of technology, large image databases have become reality. Pictures in these databases were mainly described with keywords, but due toinsufficiency of such description, the need for different approach to imageindexing and retrieval has arisen. Content-based image retrieval is an alternative to textual based systems. Images are indexed on the basis of their actual content, features like color, texture and shape are presented numerically. In retrieval process, features for input image are extracted with the same algorithm as used for pictures already stored in the database, and values are compared. Such systems are known as CBIR (content-based image retrieval) systems. Basic characteristics of CBIR systems, which are freely available on the Internet, are presented. The systems are compared with respect to the environment in which they were built, applied features for content description and ability of user interface. |