Department of Image Processing

In the first part of the talk author concentrates on the removal of moire
patterns, which may appear during film-to-video transfer using Telecine
devices. A new suppression algorithm using spectral analysis is presented and applied
for real video sequences. This non-linear filter is based on thresholding of
the magnitude of the Fourier spectrum of the image. The talk also considers
the use of overlapped block processing in order to reduce the effect of
ringing artefacts that could appear due to the non-stationarity of the moire
pattern. This work was funded by the EU's as part FP6 IST programme. It is carried
out within the BRAVA project (``Broadcast Restoration Through Video
Analysis'')

The problem of automatic defect recognition and classification for vision
systems development will be discussed in the second part of the talk. The
main objectives of such systems are defect recognition and classification
based on known features. The classification function is designed using
cluster analysis. Two stages approach is proposed. On the first offline
stage of classification a teaching process has been employed. On the second
online stage inspection image is classified using its features comparison
with the closest medians in real time. Comparative analysis with the
state-of-the-art classification methods has demonstrated an efficiency of
the proposed approach. Examples described here relate specifically to
semiconductor industry but can be adopted to other manufacturing processes.
This work is funded in part by VisionXtreme Pte Ltd.

11:00, room 25