Konferenční příspěvek

Horáček O., Flusser J.

Doktorandské dny 2007

Česká technika ČVUT

Praha

2007

978-80-01-03913-7

Ing. Ondřej Horáček, Ph.D. (ÚTIA - Oddělení zpracování obrazové informace)

image identification, decision tree

The task of the paper is to find originals of modified images, tipicallz stolen and republished on the web. Our problem is specific in terms of the database size millions of photos), demanded speed of the search (seconds), and unknown image modifications (loss of quality, radiometric degradation, etc.). The proposed method is based on image preprocess for normalization, retrieval of candidates from image index, and the candidate verification. Based on wide experiments, it was shown that the success rate of the search depends on the level of image modification.