TY - GEN
T1 - Dalgacik uzayinda öǧrenmeye dayali sayisal ses damgalama
AU - Kirbiz, Serap
AU - Günsel, Bilge
PY - 2006
Y1 - 2006
N2 - Most of the watermark (WM) decoding schemes use correlation-based methods because of their simplicity. Generally, a decision threshold specified semi-automatically is used at the decoding site. The main problem of the correlation-based decoders is the existence of undesirable correlation between the embedded signal and the host signal that makes the decision threshold specification harder, especially in noisy channels. In this paper, WM decoding is modeled as a pattern recognition problem, thus eliminates the threshold specification problem by learning the embedded data in wavelet domain followed by a nonlinear classification. Furthermore, the encoding performance is improved by perceptual control of Watermark-to-Signal-Ratio (WSR) without disturbing imperceptibility. When the WSR is higher than -30 dB, the decoding and detection performances of the developed system are greater than 99% and 98%, respectively. System false alarm ratios remain less than 2%.
AB - Most of the watermark (WM) decoding schemes use correlation-based methods because of their simplicity. Generally, a decision threshold specified semi-automatically is used at the decoding site. The main problem of the correlation-based decoders is the existence of undesirable correlation between the embedded signal and the host signal that makes the decision threshold specification harder, especially in noisy channels. In this paper, WM decoding is modeled as a pattern recognition problem, thus eliminates the threshold specification problem by learning the embedded data in wavelet domain followed by a nonlinear classification. Furthermore, the encoding performance is improved by perceptual control of Watermark-to-Signal-Ratio (WSR) without disturbing imperceptibility. When the WSR is higher than -30 dB, the decoding and detection performances of the developed system are greater than 99% and 98%, respectively. System false alarm ratios remain less than 2%.
UR - https://www.scopus.com/pages/publications/34247144074
U2 - 10.1109/SIU.2006.1659800
DO - 10.1109/SIU.2006.1659800
M3 - Konferans katkısı
AN - SCOPUS:34247144074
SN - 1424402395
SN - 9781424402397
T3 - 2006 IEEE 14th Signal Processing and Communications Applications Conference
BT - 2006 IEEE 14th Signal Processing and Communications Applications Conference
T2 - 2006 IEEE 14th Signal Processing and Communications Applications
Y2 - 17 April 2006 through 19 April 2006
ER -