Title :
Archive film defect detection based on a hidden Markov model
Author :
Wang, Xiaosong ; Mirmehdi, Majid
Author_Institution :
Dept. of Comput. Sci., Univ. of Bristol, Bristol
Abstract :
We propose a novel statistical approach to detect defects in digitized archive film by using temporal information across a number of frames modeled with an HMM. The HMM is trained for normal observation sequences and then applied within a framework to detect defective pixels by examining each new observation sequence and its subformations via a leave-one-out process. We compare against state-of-the-art results to demonstrate that the proposed method achieves better detection rates, with fewer false alarms.
Keywords :
hidden Markov models; image sequences; object detection; statistical analysis; archive film defect detection; hidden Markov model; normal observation sequences; statistical approach; Availability; Broadcast technology; Computer science; Computer vision; Degradation; Detectors; Hidden Markov models; Image restoration; Motion detection; Quality assessment;
Conference_Titel :
Image Analysis for Multimedia Interactive Services, 2009. WIAMIS '09. 10th Workshop on
Conference_Location :
London
Print_ISBN :
978-1-4244-3609-5
Electronic_ISBN :
978-1-4244-3610-1
DOI :
10.1109/WIAMIS.2009.5031490