Signal Processing, Image Processing and Pattern Recognition (eBook)

International Conference, SIP 2009, Held as Part of the Future Generation Information Technology Conference, FGIT 2009, Jeju Island, Korea, December 10-12, 2009. Proceedings (Communication

Dominik Slezak, Sankar K. Pal, Byeong-Ho Kang, Junzhong Gu, Hideo Kuroda, Tai-hoon Kim (Eds.) (Herausgeber)

eBook Download: PDF

2009 | 1. Auflage
341 Seiten
Springer-Verlag
978-3-642-10546-3 (ISBN)

Infos

This book constitutes the proceedings of the International Conference on Signal Processing, Image Processing and Pattern Recognition, SIP 2009, held as part of the Future Generation Information Technology Conference, FGIT 2009, held on Jeju Island, Korea, December 10-12, 2009. The 38 papers presented in this volume were carefully reviewed and selected from numerous submissions. The topics covered are from multifaceted aspects of signal processing, image processing and pattern recognition.

Inhalt

Title Page 2
Foreword 5
Preface 7
Organization 8
Table of Contents 9
A Blind Image Wavelet-Based Watermarking Using Interval Arithmetic 13
Introduction 13
Interval Arithmetic 14
Interval Wavelet Decomposition 14
Watermarking Algorithm 15
Considerations on the Proposed Algorithms 16
The Choice of Parameters 16
Relationship between Our Method and the HVS 17
Experimental Results 18
Conclusion 20
References 20
Hand Gesture Spotting Based on 3D Dynamic Features Using Hidden Markov Models 21
Introduction 21
Hidden Markov Models 22
3D Dynamic Feature Extraction 23
Gesture Spotting and Recognition System 24
Experimental Results 25
Isolated Gesture Recognition 25
Meaningful Gesture Spotting Test 26
Conclusion and Future Work 27
References 28
Objective Quality Evaluation of Laser Markings for Assembly Control 29
Introduction 29
Marking Evaluation 30
Marking Segmentation and Template Matching 30
Distortion Correction by Raster Alignment 31
Poll about Human Perception 32
Evaluation Methods 33
SystemConstruction 34
Verification 34
Conclusion 36
References 36
An Improved Object Detection and Contour Tracking Algorithm Based on Local Curvature 37
Introduction 37
Active Contour Model 38
Proposed Algorithm 39
Curvature Threshold and Inserting Additional Snake Points 39
Object Contour Tracking 40
Inserting and Deleting Snake Points 40
Experiments 41
Performance of Detection Analysis and Comparison 41
Performance of Tracking Analysis and Comparison 42
Conclusions 44
References 44
An Efficient Method for Noisy Cell Image Segmentation Using Generalized a-Entropy 45
Introduction 45
Entropy of Generalized Distributions 46
Proposed Segmentation Method 48
Preprocessing 48
Entropies Calculation 48
Image Thresholding 48
Morphology-Based Operations 49
Overlapping Cancelation 49
Non-objects Removal 49
Experimental Results 49
Conclusion 51
References 52
An Algorithm for Moving Multi-target Prediction in a Celestial Background 53
Introduction 53
Prediction of Moving Multi-targets 54
Targets Capture 54
Calculation of Targets Number and Coordinates 54
Image Block Processing 55
Target Prediction 56
Algorithm Simulation 57
Conclusion 58
References 59
Automatic Control Signal Generation of a CCD Camera for Object Tracking 60
Introduction 60
Signal to Control CCD Cameras 61
Creation of CCD Camera Control Signals 61
Creation of Pan Signals 62
Creation of Tilt Signals 63
Object Tracking Test of the CCD Camera 63
Initial Starting and Acceleration of CCD Camera Pan/Tilt 64
Effect of Frame Frequency 64
Effect of the Size of Pan/Tilt Signals 65
Object Tracking of CCD Camera 66
Conclusion 67
References 67
An Efficient Approach for Region-Based Image Classification and Retrieval 68
Introduction 68
Multi-level Neural Networks 69
Image Segmentation 70
Feature Extraction 71
Wavelet Decomposition 71
Color Moments 71
Proposed Approach 72
Preprocessing 72
Segmentation 73
Feature Extraction 73
Feature Normalization 73
Classification of Image Regions 73
Experimental Results 74
Conclusion 75
References 75
An Improved Design for Digital Audio Effect of Flanging 77
Introduction 77
Generation of Flanging Effect 77
The General Model 78
The Modified Model 78
Simulation Experiments and Result Analysis 79
Comparison of Modified Model with General Model 79
Performances of Modified Model for Different Modulation Waveforms 81
Conclusion 82
References 82
Robust Speech Enhancement Using Two-Stage Filtered Minima Controlled Recursive Averaging 84
Introduction 84
Overview of the Filtering Stage 85
Concept of Pre-processing 85
Spectral Gain Calculation 87
Enhancement Using FMCRA 87
Validation of the Two-Stage Progress 88
Noise Estimation 88
Experiments 89
Conclusions 91
References 92
Automatic Colon Cleansing in CTC Image Using Gradient Magnitude and Similarity Measure 94
Introduction 94
Proposed Method 95
Preprocessing 95
Histogram Peak Classification 96
Similarity Measure Classification 97
AT vs. ATT Layers 98
Reconstruction 99
Experimental Results 99
Discussion and Conclusions 100
References 101
A Scale and Rotation Invariant Interest Points Detector Based on Gabor Filters 102
Introduction 102
Gabor Functions 103
Rotation Invariant Interest Points Detection 104
Scale Selection in Gabor Scale-Space 105
Scale Invariant Interest Points Detection 106
Comparative Evaluation 107
Conclusion and Future Work 108
References 109
Signature Verification Based on Handwritten Text Recognition 110
Introduction 110
Related Work 111
Signature Recognition System 111
Preprocessing 111
Feature Extraction 111
Feature Normalization 115
Signature Verification 115
Experimental Results and Discussions 116
Conclusions 117
References 117
Effect of Image Linearization on Normalized Compression Distance 118
Introduction 118
Methodology 120
Kolmogorov Complexity and Derivations 120
Linearization Methods 121
Null Hypothesis Test 122
Dataset and Transformations 123
CompLearn 124
Statistical Analysis 125
Results 125
Discussion and Conclusion 126
Future Work 127
References 128
A Comparative Study of Blind Speech Separation Using Subspace Methods and Higher Order Statistics 129
Introduction 129
ICA Model 130
Blind Speech Separation Using High-Order Statistics 131
Separation of Mixed Speech Signals by OPCA 132
Experiments and Results 133
Conclusion 135
References 135
Automatic Fatigue Detection of Drivers through Yawning Analysis 137
Introduction 137
Literature Review 138
Proposed Approach 139
Image Acquisition 139
Face Detection and Tracking 139
Mouth Detection and Pupil Detection 140
Yawning Analysis and Driver Fatigue Monitoring 143
Experimental Results 143
Conclusion and Future Work 143
References 144
GA-SVM Based Lungs Nodule Detection and Classification 145
Introduction 145
Related Work 146
Proposed Method 147
Threshold Block 147
Background Removal 148
Edge Detection and Thinning 148
Lungs Border Identification and Reconstruction 148
Filling and Lungs Part Extraction 148
Histogram Based Threshold and Cleaning 148
Extraction of Region of Interests (ROIs) 149
Pruning of ROIs 150
Features Extraction and Classification 150
Experimental Results and Discussion 150
References 152
Link Shifting Based Pyramid Segmentation for Elongated Regions 153
Introduction 153
Literature Review 155
Overview 155
Segmentation Algorithms 156
Region Similarity and Unforced Linking 156
Pyramid Image Segmentation Algorithm 157
Creating the Initial Image Pyramid 157
Testing Similarity of Two Regions, Unforced Linking and Tie-Breaking Rule 157
Candidate Parents 158
Pyramid Segmentation 159
Experimental Results 160
Segmentation of Basic Shapes 160
Segmentation of Other Imagery 161
Future Work 163
References 163
A Robust Algorithm for Fruit-Sorting under Variable Illumination 165
Introduction 165
Experimental Set-Up 166
Methodology 166
Pre-processing 167
Defect Segmentation 168
Results 169
Conclusion 171
References 171
Selection of Accurate and Robust Classification Model for Binary Classification Problems 173
Introduction 173
Literature Review 174
One Class Classifier 174
Two Class Classifier 175
Experiments 175
Experimental Setup 175
Data Sets 175
Multi Class Classifier 175
One Class Classifier 176
Results and Discussion 176
Receiver Operating Curve (ROC) 177
Statistics (Pair Wise Measure) 177
Cross Validation Error 179
Conclusion 179
References 179
Robust Edge-Enhanced Fragment Based Normalized Correlation Tracking in Cluttered and Occluded Imagery 181
Introduction 181
EEFNC Tracking Framework 182
Experimental Results 185
Conclusion 187
References 188
Robust and Imperceptible Watermarking of Video Streams for Low Power Devices 189
Introduction 189
Background 190
Proposed Method 192
Test Results 193
Conclusions and Future Work 194
References 196
A New Ensemble Scheme for Predicting Human Proteins Subcellular Locations 197
Introduction 197
Materials and Methods 198
Proposed Method 198
Evaluation Methods 200
Results and Discussions 201
Conclusion 202
References 203
Designing Linear Phase FIR Filters with Particle Swarm Optimization and Harmony Search 205
Introduction 205
Particle Swarm Optimization 207
Harmony Search Optimization 208
Case Studies and Discussion 209
Conclusion 211
References 212
Blind Image Steganalysis Based on Local Information and Human Visual System 213
Introduction 213
Segmentation and Clustering the Segments 214
Feature Extraction 216
Classification 217
Experiment Result 217
Conclusions 219
References 219
An Effective Combination of MPP Contour-Based Features for Off-Line Text-Independent Arabic Writer Identification 221
Introduction 221
Proposed Approach 223
Feature Extraction 223
Weighted Edge Direction Probability Distribution Function $(f1)$ 225
Edge Length/Direction Probability Distribution Function $(f2)$ 226
Angle Probability Distribution Function $(f3)$ 226
Angle Co-occurrence Probability Distribution Function $(f4)$ 226
Cross-Correlation of Angle Co-occurrence Distribution $(f5)$ 227
Curvature Probability Distribution Function $(f6)$ 228
Experimental Results 228
Conclusion 230
References 231
Ringing Artifact Removal in Digital Restored Images Using Multi-Resolution Edge Map 233
Introduction 233
Ringing Artifacts Removal Using the DWT-Based Adaptive Edge Map 234
Wavelet Analysis for Extracting Edge Region 234
Ringing Artifacts Removal 235
Experimental Results 237
Conclusion 238
References 239
Upmixing Stereo Audio into 5.1 Channel Audio for Improving Audio Realism 240
Introduction 240
Audio Upmixing Algorithm from Stereo to 5.1 Channel Audio 241
Passive Surround Decoding Method 241
LMS-Based Upmixing Method 242
PCA-Based Upmixing Method 242
Adaptive Panning Method 243
Low-Pass Filters 244
Time Delay and ±90° Phase Shifter 244
Design and Implementation of Audio Upmixing Simulator 245
Performance Evaluation 245
Conclusion 246
References 247
Multiway Filtering Based on Multilinear Algebra Tools 248
Introduction 248
Tensor Representation and Properties 250
Tensor Filtering Problem Formulation 251
Channel-by-Channel SVD-Based Filtering 252
Tensor Filtering Based on Multimode PCA 253
Multiway Wiener Filtering 255
Simulation Results 257
Performance Criterion 258
Denoising of Color Images 258
Conclusion 259
References 260
LaMOC – A Location Aware Mobile Cooperative System 262
Introduction 262
Scenario Based Design and Development of LaMOC 263
LaMOC System 265
Architecture of LaMOC 265
Map Based Browser and LaMOC User Interface 266
Fixed Host Layer in LaMOC 267
Some Key Issues 268
Context Awareness 268
Mobile Cooperation 269
Conclusion 270
References 270
Modelling of Camera Phone Capture Channel for JPEG Colour Barcode Images 271
Introduction 271
Errors Pertinent to JPEG Images Captured on Camera Phones 272
Camera Phone Capture Channel Modelling 273
Simulation Results 275
Conclusion 276
References 278
Semantic Network Adaptation Based on QoS Pattern Recognition for Multimedia Streams 279
Introduction 279
Multimedia Network Context: RTP-Based Systems 280
Fixed RTP Header 280
Specific RTP Profiles 281
Implicit Packet Meta Header Ontology 282
IPMH Structure 283
Mapping Rules 283
Using the IPMH 284
Case Study 285
Conclusions 286
References 286
Active Shape Model-Based Gait Recognition Using Infrared Images 287
Introduction 287
Active Shape Model for Object Extraction in Infrared Images 288
Shape Variation Modeling 288
Model Fitting 288
Local Structure Modeling 289
Extraction of Gait Data 289
Experiment Results 290
Conclusion 293
References 293
About Classification Methods Based on Tensor Modelling for Hyperspectral Images 294
Introduction 294
Matrix Algebra-Based DR Method 295
HSI Representation 295
Principal Component Analysis Based DR Approach 296
Independent Component Analysis Based DR Approach 296
Projection Pursuit Based DR Approach 297
Tensor Representation and Some Properties 297
Multilinear Algebra-Based DR Method 298
Tensor Formulation of $PCA_{dr}$ and $PP_{dr}$ 298
Multilinear Algebra and $PCA$-Based DR Method 300
Multilinear Algebra and $PP$-Based DR Method 301
Experimental Results 302
Experiment on Simulated Data 302
Experiment on Real-World Data 303
Conclusion 306
References 307
Comparative Analysis of Wavelet-Based Scale-Invariant Feature Extraction Using Different Wavelet Bases 309
Introduction 309
Comparison of Feature Extraction Performance Using Different Wavelet Bases 310
Feature Extraction Using the Daubechies, Haar Wavelets 310
Feature Extraction Using Gabor Wavelet 311
Experiment Results 312
Discussion 313
References 315
A Novel Video Segmentation Algorithm with Shadow Cancellation and Adaptive Threshold Techniques 316
Introduction 316
Baseline Mode 317
Shadow Cancellation Mode 319
Adaptive Threshold Mode 320
Experimental Results 321
Conclusion 323
References 323
Considerations of Image Compression Scheme Hiding a Part of Coded Data into Own Image Coded Data 324
Introduction 324
Basic Principles of the Proposed Data Hiding Scheme 325
Image Coding Methods Using the Proposed Scheme 326
Fractal Image Coding Method 326
Image Coding Using Vector Quantization 327
Inter-frame Coding Using Motion Compensation 329
Considerations 330
Conclusion 330
References 331
Binarising SIFT-Descriptors to Reduce the Curse of Dimensionality in Histogram-Based Object Recognition 332
Introduction 332
Distance between SIFT-Descriptors 332
Proposed Method 335
Experimental Validation 336
Conclusion 338
References 339
Author Index 340

Textauszug

"A Robust Algorithm for Fruit-Sorting under Variable Illumination thresholding. (p. 153-154)

Abstract. Computer vision techniques are essential for defect segmentation in any automatized fruit-sorting system. Conventional sorting methods employ algorithms that are specific to standard illumination conditions and may produce undesirable results if ideal conditions are not maintained. This paper outlines a scheme that employs adaptive filters for pre-processing to negate the effect of varying illumination followed by defect segmentation using a localized adaptive threshold in an apple sorting experimental system based on a reference image. This technique has been compared with other methods and the results indicate an improved sorting performance. This can also be applied to other fruits with curved contours.

Keywords: Computer Vision, On-line fruit sorting, Surface defect, Adaptive thresholding.

1 Introduction

Fruit inspection and grading is an indispensable horticultural procedure. Uniformity in size, shape and colour are few of the many parameters that are vital in determining consumer acceptance. While the task at hand is to develop a machine vision system that identifies defective fruits based on odd shapes and surface defects, and to categorize them depending on consumer acceptability, the objective has to be accomplished with certain constraints [1].

Such a system has to be operable at high speeds suitable for real-time processing yielding a high throughput, must inspect the entire fruit surface, must be adaptable to varying fruit size, shape etc., and be applicable under various physical conditions like brightness, luminance etc. Over the past decade, various techniques have been proposed for defect segmentation and grading. Reference [2] uses flooding algorithm to identify and characterize different types of defects based on perimeter, area etc.

The snake algorithm discussed in [3] can be used to localize the defect and reduce false positives. Reference [4] employs a raw approach based on colour frequency distribution to associate pixels to a specific class while [5] accomplishes the same using ‘Linear discriminant analysis’ Hyper-spectral and multispectral imaging systems have also been proposed for sorting various food commodities as discussed in [6]-[7]. An inherent limitation in most of the existing techniques is their sensitivity to changing illumination conditions.

Any flash of external stimulus can result in bright patches in the captured image which could result in misclassification. Practical considerations dictate that any technique should be immune to occasional changes in external conditions and deliver acceptable performance. This paper incorporates the use of adaptive filters based on the conventional LMS algorithm as a pre-processing step prior to segmenting defects using an adaptive threshold. This paper has been organized as follows. Section 2 explains the components of the practical set-up used to capture images of the fruit to be sorted. Section 3 discusses the proposed methodology for pre-processing and defect segmentation. Results of the experiment have been tabulated and discussed towards the end."

Produkt-Details

• Erscheint lt. Verlag: 1.1.2009
• Sprache: englisch
• Themenwelt: Informatik ► Theorie / Studium ► Künstliche Intelligenz / Robotik
• Themenwelt: Mathematik / Informatik ► Mathematik ► Analysis
• Themenwelt: Technik
• Themenwelt: Wirtschaft ► Betriebswirtschaft / Management ► Wirtschaftsinformatik
• ISBN-10: 3-642-10546-7 / 3642105467
• ISBN-13: 978-3-642-10546-3 / 9783642105463