| Summary: | 碩士 === 國立中正大學 === 電機工程研究所 === 83 === A new wavelet-based automatic multi-level thresholding techn-
ique is proposed. The new technique is a generalized version
of the method proposed by Olivo. In his paper, Olivo proposed
to use a set of dilated wavelets to convolve with the histogram
of an image. For each scale, a set of thresholds was determined
aut- omatically based on the rules he proposed. However, Olivo
did not provide a systematic way to decide an exact set of
thresholds which corresponds to a specific scale that can make
the segmenta- tion result best. In this thesis, we propose to
use a cost func- tion as a guidance to solve the above
problem. Experimental results show that our approach can
always automatically select the best scale for performing multi-
level thresholding.
|
|---|
