Signal Analysis Research (SAR) Group - RNet - Ryerson University

Recommendations

Info

ing a large number of cells in Hough-Radon space shifts the peak of the accumulator to the neighbor cells and consequently results in a wrong detection of the slope in TFD. Therefore, we see in Figure 3 that DPPT-based method outperforms HRT-based algorithm in most of the attack types with a total detection of 92% compared to 87%. Also, comparing the complexity order of HRT-based and DPPT-based techniques, we conclude that the DPPT-based method is more practical for real-time applications. Figure 4, shows the complexity order and running time based on Pentium IV, CPU 2.66GHz and 512MB of RAM. DPPT-based watermark extraction is about 55 times faster than HRT-based algorithm. As we observe in Figure 3, the detection result for the BCH coding and repetition codings have almost the same detection rates, but DPPT-based method offers better or in some cases equal results when compared to REP and BCH codings. Figure 5 shows the detection results considering BER in the received message. As we see in this figure, both DPPT and BCH detect 100% watermark messages successfully up to a BER of 17%. However, the maximum BER that BCH detects a watermark correctly is 22% with 17% detection, while DPPT shows 50% detection rate at a BER of 28%. To highlight the outstanding performance of DPPT at high BERs, we calculate the watermark detection rate for BERs bigger than 17%. We see that the DPPT-based method offers 52% detection rate in higher BERs, while BCH and Repetition codings have 47% and 41% detection rates. Figure 4. Order of complexity of each coding schemes used to code the watermark message 5. Conclusions In this paper, we compared FEC-based and chirp-based post processing methods in watermarking. The robustness of the proposed techniques was tested against checkmark benchmark attacks. The DPPT-based and BCH-based methods were able to compensate the BER of up to 17%. The DPPT-based post processing offered the highest detection rate of 92%, and showed the highest detection rate for BERs of higher than 17%. Also, we compared the computation complexity of the proposed methods; BCH, repetition and DPPT-based methods have almost the same complex- Proceedings of the 2006 International Conference on Intelligent Information Hiding and Multimedia Signal Processing (IIH-MSP'06) 0-7695-2745-0/06 $20.00 © 2006 Successful watermark estimation(%) 100 90 80 70 60 50 40 30 20 10 HRT REP BCH DPT 0 0 5 10 15 20 25 30 35 40 BER of the received watermark message Figure 5. Watermark detection under different bit error rates. ity, while HRT has a complexity of 55 times higher than the other methods, and this is because HRT operates on the TF plane, and calculates the accumulator value for all the cells in Hough-Radon plane. References [1] S. Erkucuk, S. Krishnan, and M. Zeytinoglu. Robust audio watermarking using a chirp based technique. IEEE Intl. Conf. on Multimedia and Expo, 2:513–516, July 2002. [2] D. Kirovski and H. Malvar. Spread-spectrum watermarking of audio signals. IEEE Transactions on Signal Processing, special issue on data hiding, 51:1020–1034, April 2003. [3] L. Le and S. Krishnan. Time-frequency signal synthesis and its application in multimedia watermark detection. EURASIP Journal on Applied Signal Processing, 2006:Article ID 86712, 14 pages, 2006. [4] J. Lee, H. Kim, and J. Lee. Information extraction method without original image using turbo code. Proc. International Conference on Image Processing, Greece, 3:880–883, October 2001. [5] S. Peleg and B. Friedlander. The discrete polynomialphase transform. IEEE Transactions on Signal Processing, 43:1901–1914, August 1995. [6] S. Pereira, S. Voloshynovskiy, M. Madueno, S. Marchand- Maillet, and T. Pun. Second generation benchmarking and application oriented evaluation. In Information Hiding Workshop III, Pittsburgh, PA, USA, April 2001. [7] A. Ramalingam and S. Krishnan. Robust image watermarking using a chirp detection-based technique. IEE Proceedings on Vision, Image and Signal Processing, 152:771–778, December 2005. [8] R. Rangayyan and S. Krishnan. Feature identification in the time-frequency plane by using the Hough-Radon transform. IEEE Trans. on Pattern Recognition, 34:1147–1158, 2001. Authorized licensed use limited to: Ryerson University Library. Downloaded on July 7, 2009 at 11:31 from IEEE Xplore. Restrictions apply. 31
2006 International Joint Conference on Neural Networks Sheraton Vancouver Wall Centre Hotel, Vancouver, BC, Canada July 16-21, 2006 Automatic Content-Based Image Retrieval Using Hierarchical Clustering Algorithms Kambiz Jarrah, Student Member, IEEE, Sri Krishnan, Senior Member, IEEE, and Ling Gum, Senior Member, IEEE Amt-The overall objective of this paper is to present a methodology for guiding adaptations of an RBF-based relevance feedback network, embedded in automatic content- based image retrieval (CBIR) systems, through the principle of unsupervised hierarchical clustering. The self-organizing tree map (SOTM) is essentially attractive for our approach since it not only extracts global intuition from an input pattern space but also injects some degree of localization into the discriminative process such that maximal discrimination becomes a priority at any given resolution. The main focus of this paper is twwfold: introducing a new member of SOTM family, the Directed SOTM (DSOTM) that not only provides a partial supervision on cluster generation by forcing divisions away from the query class, but also presents a flexible verdict on resemblance of the input pattern as its tree structure grows; and modifying the current structure of the normalized graph cuts (Ncut) process by enabling the algorithm to determine appropriate number of clusters within an unknown dataset prior to its recursive clustering scheme through the principle of self-or ganizing normalized graph cuts (SONcut). Comprehensive comparisons with the Self-Organizing Feature Map (SOFM), SOTM, and Ncut algorithms demonstrate feasibility of the proposed methods. I INTRODUCTION Content-based image retrieval (CBIR) relies on characterization of images based on their visual contents. These visual contents consist of low-level features including colour, texture, shape, etc.- that offer a multidimensional vector representation of an image within the feature space. One of the major requirements for designing an effective CBIR system is to reduce the gap between low-level features and high-level concepts by tailoring the human perceptual subjectivity to the retrieval process. Human-computer interaction (HCI) systems have demonstrated a successful training the system with suitable samples (images). This dependency of the system on users' inputs may add excessive human errors to the adaptation process due to subjective interpretations of image contents by each individual. To overcome this problem, an unsupervised learning approach with a hierarchical architecture is required to guide these adaptations automatically and more toward relevant samples. SOTM has show an effective behavior in minimizing human interactions and automating the search process by efficiently classifying an unknow and non- uniform data space into more meaningful clusters. The main focus of this paper is as follows: a) introducing a new member of SOTM family, the Directed SOTM (DSOTM), that dynamically controls generation of new centres and decides on resemblance of input samples, with respect to the query, during the learning phase of the algorithm; and b) modifying the current structure of the normalized graph cuts (Ncut) algorithm [2] to make it more adaptive to the nature of the input pattern by adding a self- determination mechanism to its algorithm to decide on appropriate number of clusters prior to its iterative clustering process. We call the modifiedNcut, the self-organizing Ncut (SONcut). This paper provides some details on both DSOTM and SONcut algorithms in Section 2; Section 3 presents an overall description on the structure of CBIR system used in this work; a comprehensive comparison between the proposed classifiers and their conventional counterparts is also presented in Section 4; Section 5 concludes the paper with some remarks. 11. UNSUPERVIXD CLUSTERING APPROACHES behavior for this purpose [I]. In such systems, users directly In this section, an overview of the proposed unsupervised supervise the learning process by constantly providing and hierarchical clustering algorithms using DSOTM and SONcut is presented. This work was supported by Natural Sciences andEngineering Research A. Drected Sekf-Organ~zmg Tree Map (DSOTM) Council of Canada (NSERC) and Ryerson Graduate Scholarship Program K Jarrah, barrak@e.ryerson.ca, is affiliated with the Multimedia Research Laboratory (RML) and Signal Analysis Research Group (SAR), L31 is an unsupervised machine learning 'gorithm and is inspired by principles found in Kohonen's self- Ryerson University ( mw ryerson ca), Toronto, Canada. S Knshnan, hisknan@e.ryersora.ca, is the char of Department of Electrical and Computer Engineering, Ryerson University, Toronto, Canada, andis affiliatedwith the Signal halysis Research Group (SAR) at organizing feature map (SOFM) [4]. The tree structure of the SOTM is constructed by randomly selecting an isolated root node (centre) and the same university L Gum, dguan@e.ryerson.ca, is the Canada Research Char, Ryerson University, Toronto, Canada, and is affiliated with the Multimedia Research repeatedly presenting the remaining of the patterns to the network. The pattern (sample) which is found to be closest to the centre with respect to current similarity measurement Laboratory (RML) at the same university 0-7803-9490-9/06/$20.00/©2006 IEEE 3532 32 Authorized licensed use limited to: Ryerson University Library. Downloaded on July 7, 2009 at 11:49 from IEEE Xplore. Restrictions apply.
Page 1 and 2: Signal Analysis Research (SAR) Grou
Page 3 and 4: 2006.05 Support Vector Machines Bas
Page 5 and 6: 2001.05 Instantaneous Mean Frequenc
Page 7 and 8: Class A Class B TWFB Mapping Discri
Page 9 and 10: as an added advantage of this appro
Page 11 and 12: Combining Vocal Source and MFCC Fea
Page 13 and 14: probability distribution for calcul
Page 15 and 16: Proceedings of the 29th Annual Inte
Page 17 and 18: Fig. 1. Typical images of the small
Page 19 and 20: This full text paper was peer revie
Page 21 and 22: Frequency 1 0.9 0.8 0.7 0.6 0.5 0.4
Page 23 and 24: Frequency TABLE I RESULTS WITH LINE
Page 25 and 26: Emotion Recognition Using Novel Spe
Page 27 and 28: points [1, 2, 3] (Fig. 2). SVM is b
Page 29 and 30: A WATERMARKING METHOD FOR SPEECH SI
Page 31 and 32: In order to exploit the masking eff
Page 33 and 34: Chirp-based image watermarking as e
Page 35: 3.2.2 Discrete Polynomial Phase Tra
Page 39 and 40: Fig 2 Two-dimensional mapping (Left
Page 41 and 42: p3 Feature Extraction u Database +
Page 43 and 44: 1424403677/06/$20.00 ©2006 I
Page 45 and 46: = − = K ≤
Page 47 and 48: DISCRETE POLYNOMIAL TRANSFORM FOR D
Page 49 and 50: 3.2. Watermark detection Fig.2 show
Page 51 and 52: IMPROVING POSITION ESTIMATES FROM A
Page 53 and 54: _ . r W-. n r We tried two ways of
Page 55 and 56: Acknowledgements This work of Ryers
Page 57 and 58: ing two consecutive keys. Another c
Page 59 and 60: Table 1. Experimental Results for F
Page 61 and 62: D as { gγ γ ∈ Γ, g = 1} = γ ,
Page 63 and 64: frequency parameters issued from th
Page 65 and 66: necessity of prediction, controllin
Page 67 and 68: 4. Experimental Results The objecti
Page 73: Proceedings of the 2005 IEEE Engine
Page 78 and 79: the whole spectrum but on non-overl
Page 80 and 81: Identification Rate 1 0.9 0.8 0.7 0
Page 82 and 83: signals. On some occasions, when us
Page 84 and 85: For our first test, we recorded two
Page 86 and 87:
Frequency bands F4 F3 F2 F1 ME5 s1
Page 88 and 89:
as F1, F2, F3 and F4 as shown in Fi
Page 90 and 91:
Figure. 1. Motion Vector magnitudes
Page 92 and 93:
All the above descriptor were quant
Page 94 and 95:
2. METHODOLOGY 2.1. Local Discrimin
Page 96 and 97:
. each group, the posterior probabi
Page 98 and 99:
A NOVEL ROBUST IMAGE WATERMARKING U
Page 100 and 101:
where n is the distortion component
Page 102 and 103:
A Novel Way of Lossless Compression
Page 104 and 105:
111. IMPLEMENTATION As we have pres
Page 106 and 107:
CONTENT BASED AUDIO CLASSIFICATION
Page 108 and 109:
Entropy 4.5 4 3.5 3 2.5 2 1.5 1 0.5
Page 110 and 111:
MODIFIED LOCAL DISCRIMINANT BASES A
Page 112 and 113:
Tree Decomposition (0,0) (1,0) (1,1
Page 114 and 115:
RADIO OVER MULTIMODE FIBER FOR WIRE
Page 116 and 117:
3. COMPARISON OF MULTIMODE FIBER AN
Page 118 and 119:
SUB-DICTIONARY SELECTION USING LOCA
Page 120 and 121:
0 : SI 92 r3 54 =-ax Tirnep"idfh :
Page 122 and 123:
Proceedings of the 25h Annual Inter
Page 124 and 125:
estimated noise generated as the ou
Page 126 and 127:
ROBUST AUDIO WATERMARKING USING A C
Page 128 and 129:
where 0 is the angle of the ray pat
Page 130 and 131:
TIME-FREQUENCY FILTERING OF INTERFE
Page 132 and 133:
3. INTERFERENCE DETECTION. nouen AN
Page 134 and 135:
A GENERAL PERCEPTUAL TOOL FOR EVALU
Page 136 and 137:
Fig. 2. Snapshot of the GUI used fo
Page 138 and 139:
Non-Stationary Noise Cancellation i
Page 140 and 141:
signal and noise spectra overlap, f
Page 142 and 143:
Fig. 4: Output of the Comb filter.
Page 144 and 145:
Indoor infrared transmission suffer
Page 146 and 147:
The inverse wavelet transform is de
Page 148 and 149:
The simulations has been done using
Page 150 and 151:
Figure 6: The original Gaussian noi
Page 152 and 153:
147 Authorized licensed use limited
Page 154 and 155:
Page 156 and 157:
Page 158 and 159:
Page 160 and 161:
Page 162 and 163:
Page 164 and 165:
Page 166 and 167:
Page 168 and 169:
Page 170 and 171:
Figure 2: Block diagram of the FBB
Page 172 and 173:
Figure 4: Benign mammogram before F
Page 174 and 175:
. Table 1: Compression ratios of be
Page 176 and 177:
Most Cohen’s class TFD derived fr
Page 178 and 179:
the desired frequency marginal m(w)
Page 180 and 181:
constructing an adaptive TFD and ex
Page 182 and 183:
Proceedings of the 22"d Annual EMBS
Page 184 and 185:
are: Proceedings of the 22"d Annual
Page 186 and 187:
may be written as M-1 = (z,grn)gm,
Page 188 and 189:
e 1 os 07- Ohzo5- 04- 09- 02- 01- O
Page 190 and 191:
using the denoised signals. As an i
Page 192 and 193:
signals are: 1) model-based TFD, 2)
Page 194 and 195:
compared to that in the MP dictiona
Page 196 and 197:
fied. In addition to being positive
Page 198 and 199:
08 [3] S. Peleg and B. Friedlander.
Page 200 and 201:
Proceedings - 19th International Co
Page 202 and 203:
Proceedings - 19th International Co
Page 204 and 205:
the x and y axes correspond to the
Page 206 and 207:
Fig. 5. Results with synthetic sign
Page 208 and 209:
the users and is explained in next
Page 210 and 211:
,-t 1 2 J 4 5 e 7 e e 10 SNR (I" de
Page 212 and 213:
'il! (c) (a) Weakea User 2nd Strong
Page 214 and 215:
18th Annual International Conferenc
Page 216 and 217:
quisition board and Lab Windows (Na
Page 218 and 219:
Table 1: Comparison of different cl
Page 220:
K. Umapathy and S. Krishnan, Low bi
show all

Signal Analysis Research (SAR) Group - RNet - Ryerson University

You also want an ePaper? Increase the reach of your titles

Delete template?

Save as template?