IEEE Transaction on Image processing (October)

Table of contents :
01510675.pdf……Page 1
01510676.pdf……Page 3
Fig. 1. (Top) Fixed-length channel codewords with variable-lengt……Page 4
Proof: Let $R$ be an $N$ -packet EPS. Then, $ um _{i=0}^{N}P_{i……Page 5
V. R ESULTS……Page 6
TABLE IV E XPECTED MSE AT V ARIOUS T RANSMISSION R ATES FOR A RO……Page 7
D. N. Rowitch and L. B. Milstein, On the performance of hybrid F……Page 8
I. I NTRODUCTION……Page 9
II. P REVIOUS W ORK……Page 10
C. Fourier Mellin Transform……Page 11
III. M ODIFIED LMA……Page 12
B. Modified Levenberg Marquardt Algorithm……Page 13
Fig. 5. $chi ^{2}$ curve for rotation (standard LMA)…….Page 14
IV. G LOBAL R EGISTRATION U SING L OG -P OLAR T RANSFORM……Page 15
A. Uncalibrated Test Images……Page 16
B. Calibrated Test Images……Page 17
C. Image Mosaics……Page 18
R. Szeliski and H.-Y. Shum, Video mosaics for virtual environmen……Page 19
L. Wang, S. Kang, R. Szeliski, and H. Shum, Optimal texture map……Page 20
I. I NTRODUCTION……Page 22
II. M ULTISCALE I MAGE R EPRESENTATION B ASED ON O VERCOMPLETE W……Page 23
B. Measuring Singularity Strength With WT and Multifractals……Page 24
IV. P ROPOSED D ENOISING A LGORITHM……Page 25
A. MMSE-Based Filtering……Page 26
Fig.€3. Illustration of the classification of noisy wavelet coef……Page 27
TABLE II P ERFORMANCE (PSNR IN D ecibels ) OF THE P ROPOSED WMFS……Page 28
C. Summary of the Proposed Algorithm……Page 29
Fig.€7. Denoised image of Peppers using the proposed WMFSD algor……Page 30
V. E XPERIMENTAL R ESULTS……Page 31
VI. C ONCLUSION……Page 32
M. J. Turner, J. M. Blackledge, and P. R. Andrews, Fractal Geome……Page 33
J.-M. Ghez and S. Vaienti, On the wavelet analysis for multifrac……Page 34
I. I NTRODUCTION……Page 35
II. M ODIFIED R ESTORATION P ROBLEM……Page 36
III. E FFICIENT A PPROXIMATION……Page 37
IV. E XPERIMENTS……Page 38
V. C ONCLUSION……Page 39
A. V. Oppenheim, R. W. Schafer, and J. R. Buck, Discrete-Time Si……Page 40
Restoration Based on Partial Differential Equations and Variatio……Page 41
B. Outline……Page 42
Fig. 2. Intensity feature for a group formed by the edges couple……Page 43
A. Local Features……Page 44
Fig. 3. Behavior of the circle-fitting related measures. (a) Bot……Page 45
Fig. 5. Reconstruction examples for fading spare edges…….Page 46
C. Spare Edges Reconstruction……Page 47
B. Inpainting of a Side Strip With Continuous Contour Bounded by……Page 48
A. Qualitative Evaluation……Page 49
B. Quantitative Evaluation……Page 50
C. A Real Case Experiment……Page 51
D. Comparisons With Other Algorithms……Page 52
VI. C ONCLUSIONS AND F UTURE W ORK……Page 53
M. Wertheimer, Laws of organization in perceptual forms, in A So……Page 54
I. I NTRODUCTION……Page 56
A. LPA Kernel Estimates……Page 57
B. Idea of Deblurring Algorithm……Page 58
1) Basic Steps: We develop the spatially adaptive RWI deconvolut……Page 59
III. A SYMPTOTIC T HEORY……Page 60
Proposition 1: Consider the RI-RWI estimate. Assume that 1) 4) h……Page 61
Fig. 4. ICI adaptive scales $h^{+}$ for four directions shown by……Page 62
Fig.€5. Reconstruction of Cameraman image. (a) True image. (b) N……Page 63
E. J. Candès and D. L. Donoho, Recovering edges in ill-posed inv……Page 64
A. N. Tikhonov and V. Y. Arsenin, Solution of Ill-Posed Problems……Page 65
A. Review of the Adaptive Median Filter……Page 66
2. (Replacement): Since all pixels in $ {cal N}^{c}$ are detect……Page 67
A. Configuration……Page 68
Fig. 3. Restoration results of different filters. (a) Corrupted……Page 69
B. Denoising Performance……Page 70
TABLE II C OMPARISON OF CPU T IME IN S ECONDS……Page 71
E. Bingham and H. Mannila, Random projection in dimensionality r……Page 72
I. I NTRODUCTION……Page 73
B. Mutual Information Between the Image Intensity and the Label……Page 74
C. Energy Functional……Page 75
C. Gradient Flow for the Information-Theoretic Energy Functional……Page 76
A. $n$ ary Segmentation Problem and Mutual Information……Page 77
V. E XPERIMENTAL R ESULTS……Page 78
Fig. 5. Evolution of the curve on a synthetic image without the……Page 79
Fig. 8. Evolution of the curve on a synthetic image; unimodal ve……Page 80
Fig. 9. Segmentations of the image in Fig.€7(a) with various ini……Page 81
Fig. 11. Evolution of the curve on a synthetic image; uniform (f……Page 82
VI. C ONCLUSION……Page 83
Proof: The inequality is basically the data processing inequalit……Page 84
• Compute sample mean and sample variance of ${ I_{1}, ldots ,……Page 85
D ERIVATION OF THE C URVE E VOLUTION F ORMULA……Page 86
Derivation……Page 87
J. Kim, J. W. Fisher, III, M. Cetin, A. Yezzi, Jr., and A. S. Wi……Page 88
I. I NTRODUCTION……Page 90
II. D EPTH OF F IELD AND L OW DOF……Page 91
B. HOS Map Simplification by Morphological Filtering by Reconstr……Page 92
Fig. 4. Pictorial illustration of the proposed algorithm. (a) Lo……Page 93
1) Region Merging: Our region merging is started based on seed r……Page 94
2) Final Decision: In the preceding subsection, the focused regi……Page 95
IV. E XPERIMENTAL R ESULTS……Page 96
D. Comaniciu and P. Meer, Robust analysis of feature spaces: Col……Page 97
C. Kim and J.-N. Hwang, An integrated scheme for object-based vi……Page 98
I. I NTRODUCTION……Page 99
A. Problem Formulation……Page 100
Fig. 1. Two-dimensional ring image. (a) The ring with a coherent……Page 101
B. Local Orientation Estimation……Page 102
Fig. 5. Three-dimensional synthetic image, ring torus. (a) Compl……Page 103
7: $$displaylines{E_{b} Leftarrow umlimits_{jin{{cal N}_i……Page 104
V. S ENSITIVITY A NALYSES OF THE MRF P ARAMETERS……Page 105
B. Experiments on Real-World Medical Images……Page 106
Fig. 13. PC MRA dataset 2. The 15th and 16th slice images. (a) A……Page 107
Fig. 15. PC MRA dataset 2. (a) Volume rendered image the aneurys……Page 108
Y. Wang, T. Adali, J. Xuan, and Z. Szabo, Magnetic resonance ima……Page 109
Y. T. Cui and Q. Huang, Character extraction of license plates f……Page 110
A. Motivation and Justification for the Proposed Approach……Page 111
Fig. 2. Schematic of proposed segmentation algorithm…….Page 112
A. Motivation and Prior Work……Page 113
1) Given two color composition feature vectors $f^{1}_{c}$ and $……Page 114
A. Motivation and Prior Work……Page 115
B. Proposed Spatial Texture Features……Page 116
IV. S EGMENTATION A LGORITHM……Page 117
B. Border Refinement Using Adaptive Clustering……Page 118
Fig. 9. Illustration of border refinement…….Page 119
Fig. 11. Image segmentation using JSEG [ 12 ] with least merge s……Page 120
W. Y. Ma, Y. Deng, and B. S. Manjunath, Tools for texture/color……Page 121
D. Martin, C. Fowlkes, D. Tal, and J. Malik, A database of human……Page 122
I. I NTRODUCTION……Page 124
II. S EGMENTATION M ETHODS B ASED ON M UMFORD S HAH F UNCTIONAL……Page 125
B. Chan Vese Piecewise Smooth Model……Page 126
III. A NISOTROPIC D IFFUSION M ETHOD FOR I MAGE S MOOTHING……Page 127
2) Weight Parameters in the Two Phase Segmentation Method: It is……Page 128
3) Hierarchical Multiphase Segmentation Method: Using a piecewis……Page 129
Fig. 3. Four phase segmentation using our hierarchical method. L……Page 130
ii) The result of segmentation in step i ) (i.e., $phi $ values……Page 131
A. Segmentation Results……Page 132
Fig. 7. Segmentation of medical images. Left column: Original im……Page 133
VI. C ONCLUSION……Page 134
R. Malladi and J. A. Sethian, Image processing via level set cur……Page 135
S. Zhu and A. Yuille, Region competition: Unifying snakes, regio……Page 136
I. I NTRODUCTION……Page 137
Formulation I: Minimum distortion optimal summarization (MDOS) $……Page 138
B. Distortion State Definition and Recursion……Page 139
D. Skip Constraint……Page 140
Fig. 3. Computation complexity of the DP solution as a function……Page 141
A. Frame Distortion Metric……Page 142
Fig. 6. Frame-by-frame distortion $d (f _{k}, f _{k-1})$ plot fo……Page 143
TABLE II D ISTORTION P ERFORMANCE FOR THE F LOWER S EQUENCE: ${n……Page 144
TABLE III D ISTORTION P ERFORMANCE FOR THE F OREMAN S EQUENCE: $……Page 145
B. S. Manjunath, J.-R. Ohm, V. V. Vasudevan, and A. Yamada, Colo……Page 146
Fig. 1. Schematic diagram of a model-based vehicle tracking syst……Page 148
B. Pose Evaluation Function……Page 149
B. Determination of Translation Parameters……Page 150
Fig. 4. Angle defined by three points on the image plane…….Page 151
B. Motion Tracking……Page 152
1) Small Viewing Angle Sequence: In order to further test our al……Page 153
Fig. 12. Pose evaluation function for a car with low resolution……Page 154
T. Frank, M. Haag, H. Kollnig, and H.-H. Nagel, Characterization……Page 155
J. G. Lou, H. Yang, W. M. Hu, and T. N. Tan, Visual vehicle trac……Page 156
I. I NTRODUCTION……Page 157
A. Model Assumption……Page 158
C. Different Problem Formulation……Page 159
1) (Local) Discrete Cosine Transform (DCT): The DCT is a variant……Page 160
2. Perform $N$ times:……Page 161
A. Image Decomposition……Page 162
Fig. 5. Top: Reconstructed DCT and curvelet components by our me……Page 163
A. Variational Separation Paradigm……Page 164
B. Compression via Separation……Page 165
Corollary 1: If the image $underline {X} =underline {X}_{t}+ ……Page 166
Fig. 9. Empirical probability of success of the BP algorithm for……Page 167
E. Candès and J. Romberg, Robust uncertainty principles: Exact s……Page 168
Step 1. Initiate ${rm LUT}[~]=0$ and $N[~]=0$, where the array……Page 170
III. P ROPOSED E DGE- B ASED LUT I NVERSE H ALFTONING A LGORITHM……Page 171
C. Investigate the Distribution of Edges and Smooth Regions for……Page 172
Step 1. Call procedure building-up ELUT. Call procedure LIH to c……Page 173
IV. E XPERIMENTAL R ESULTS……Page 174
Z. Xiong, M. T. Orchard, and K. Ramchandran, Inverse halftoning……Page 175
I. I NTRODUCTION……Page 177
A. Estimating Chaotic Parameters Based on Ergodic Theory……Page 178
Fig.€2. Mean value curve of the chaotic signals generated by the……Page 179
B. Watermark Detection Using ECPM……Page 180
Fig. 5. Real mean values of the image pixels $mu_{v}^{i}$ and t……Page 181
Fig.€6. Original image of Lena used as the host data…….Page 182
Fig.€7. Theoretical and empirical BER curves versus different me……Page 183
V. R OBUSTNESS T ESTS A GAINEST A TTACKS……Page 184
C. Median Filtering……Page 185
D. Image Compression……Page 186
Fig.€14. BER performance comparison of the holographic method, t……Page 187
VI. C ONCLUSION……Page 188
H. S. Malvar and D. A. F. Florencio, Improved spread spectrum: a……Page 189
I. I NTRODUCTION……Page 190
II. P RELIMINARIES AND N OTATION……Page 191
Definition 7: [ 2 ] The Procrustes tangent coordinates of a cent……Page 192
A. Stationary Shape Activity: Shape Deformation Model in Tangent……Page 193
C. Nonstationary Shape Dynamics……Page 194
D. Particle Filtering Algorithm……Page 195
B. Partially Observed Case……Page 196
A. Dataset and Experiments……Page 197
B. ELL Versus TE: Slow and Drastic Changes……Page 198
C. ROC Curves and Performance Degradation With Increasing Observ……Page 199
Fig. 8. ELL plot for temporal abnormality detection. Abnormality……Page 200
B. Activity Sequence Identification and Tracking [39]……Page 201
S. Zhou and R. Chellappa, Probabilistic human recognition from v……Page 202
N. Vaswani, Bound on errors in particle filtering with incorrect……Page 203
I. I NTRODUCTION……Page 204
B. PicHunter……Page 205
D. Motivation……Page 206
A. Generalized Bayesian Learning Framework……Page 207
B. Estimation of ${cal Q}_{t}$ and $Theta_{t}$ for Region-Base……Page 208
TABLE I S YMBOLS AND D EFINITIONS……Page 209
D. Determination of Region Correspondence and Region Weights $w_……Page 210
E. Improvement of Region Clustering……Page 211
C. Experimental Setting……Page 212
D. Experimental Results and Discussions……Page 213
Fig. 4. Averaged accuracy versus iteration curves for GBI, GBR (……Page 214
Fig. 6. Accuracy versus iteration curves for the initial query i……Page 215
Fig. 8. Accuracy versus iteration curves for the initial query i……Page 216
VI. C ONCLUSION……Page 217
A. Jaimes, A. B. Benitez, S. F. Chang, and A. C. Loui, Discoveri……Page 218
A. Concept of Scalability……Page 219
B. KLT as a Slice Transform……Page 220
D. Empirical Observations……Page 221
Fig.€1. Low-pass slice from the second decomposition level of th……Page 222
A. Three-Dimensional Context Models……Page 223
D. Information-Theoretic Experiment……Page 224
1) Actual Results: The first aspect to examine is the attainabil……Page 225
G. Block Extension Versus Context Modeling Gain……Page 226
IV. R ANDOM A CCESSIBILITY……Page 227
B. Temporal Expansion During Synthesis……Page 228
D. Optimal Code-Block Configurations……Page 229
Fig.€10. Coding efficiency versus accessibility. (Top) Medical v……Page 230
A. Random Access Cost Calculations for Mesh-Based Motion-Adaptiv……Page 231
D. Taubman, High performance scalable image compression with EBC……Page 232
J. Liu and P. Moulin, Information-theoretic analysis of intersca……Page 233
I. I NTRODUCTION……Page 234
II. A NALYTIC P ERSPECTIVE AND M OTIVATIONS……Page 235
C. Total-Variation Regularizer……Page 236
D. Background on LSM and Propagation of Fronts……Page 237
IV. P ROPOSED M ETHOD FOR G RAYscale I MAGE U P -S AMPLING……Page 238
V. P ERCEPTUAL U NIFORMITY V ERSUS L INEARITY……Page 239
Fig.€8. Up-sampling of a portion of the cameraman image in Fig…….Page 240
VI. I MPLEMENTATION A LGORITHMS……Page 241
VII. E XPERIMENTS AND R ESULTS……Page 242
Fig.€11. Up-sampling the image in Fig. 7(c) by a factor of 25 us……Page 243
VIII. C ONCLUSION……Page 244
P. D. Welch, The use of fast Fourier transform for the estimatio……Page 245
H. H. Bauschke and P. L. Combettes, Construction of best Bergman……Page 246
MOD IMAGE AND VIDEO MODELING……Page 247
Information for Authors (Updated February 2005)……Page 248
01510700.pdf……Page 250
01510701.pdf……Page 251
Awards Board Chair, M. K AVEH Conference Board Chair, R. K. W AR……Page 252