상세정보

Image segmentation is generally the first task in any automated image understanding application, such as autonomous vehicle navigation, object recognition, photointerpretation, etc. All subsequent tasks, such as feature extraction, object detection, and object recognition, rely heavily on the quality of segmentation. One of the fundamental weaknesses of current image segmentation algorithms is their inability to adapt the segmentation process as real-world changes are reflected in the image. Only after numerous modifications to an algorithm's control parameters can any current image segmentation technique be used to handle the diversity of images encountered in real-world applications.
Genetic Learning for Adaptive Image Segmentation presents the first closed-loop image segmentation system that incorporates genetic and other algorithms to adapt the segmentation process to changes in image characteristics caused by variable environmental conditions, such as time of day, time of year, weather, etc. Image segmentation performance is evaluated using multiple measures of segmentation quality. These quality measures include global characteristics of the entire image as well as local features of individual object regions in the image.
This adaptive image segmentation system provides continuous adaptation to normal environmental variations, exhibits learning capabilities, and provides robust performance when interacting with a dynamic environment. This research is directed towards adapting the performance of a well known existing segmentation algorithm (Phoenix) across a wide variety of environmental conditions which cause changes in the image characteristics. The book presents a large number of experimental results and compares performance with standard techniques used in computer vision for both consistency and quality of segmentation results. These results demonstrate, (a) the ability to adapt the segmentation performance in both indoor and outdoor color imagery, and (b) that learning from experience can be used to improve the segmentation performance over time.


Image segmentation is generally the first task in any automated image understanding application, such as autonomous vehicle navigation, object recognition, photointerpretation, etc. All subsequent tasks, such as feature extraction, object detection, and object recognition, rely heavily on the quality of segmentation. One of the fundamental weaknesses of current image segmentation algorithms is their inability to adapt the segmentation process as real-world changes are reflected in the image. Only after numerous modifications to an algorithm's control parameters can any current image segmentation technique be used to handle the diversity of images encountered in real-world applications.
Genetic Learning for Adaptive Image Segmentation presents the first closed-loop image segmentation system that incorporates genetic and other algorithms to adapt the segmentation process to changes in image characteristics caused by variable environmental conditions, such as time of day, time of year, weather, etc. Image segmentation performance is evaluated using multiple measures of segmentation quality. These quality measures include global characteristics of the entire image as well as local features of individual object regions in the image.
This adaptive image segmentation system provides continuous adaptation to normal environmental variations, exhibits learning capabilities, and provides robust performance when interacting with a dynamic environment. This research is directed towards adapting the performance of a well known existing segmentation algorithm (Phoenix) across a wide variety of environmental conditions which cause changes in the image characteristics. The book presents a large number of experimental results and compares performance with standard techniques used in computer vision for both consistency and quality of segmentation results. These results demonstrate, (a) the ability to adapt the segmentation performance in both indoor and outdoor color imagery, and (b) that learning from experience can be used to improve the segmentation performance over time.

정보제공 :

CONTENTS
LIST OF FIGURES = Ⅸ
PREFACE = XVII
1 INTRODUCTION = 1
 1.1 Definition of Image Segmentation = 1
 1.2 Characteristics of the Image Segmentation Problem = 2
 1.3 Parameter Selection = 4
 1.4 Multi - Level Vision and Image Segmentation = 7
 1.5 Adaptive Image Segmentation = 9
 1.6 Outline of this Book = 12
2 IMAGE SEGMENTATION TECHNIQUES = 15
 2.1 Edge Detection = 15
 2.2 Region Splitting and Region Glowing = 16
 2.3 The Phoenix Image Segmentation Algorithm = 18
3 SEGMENTATION AS AN OPTIMIZATION PROBLEM = 25
 3.1 Representation of Segmentation Quality = 25
 3.2 Selection of an Optimization Technique = 28
 3.3 Genetic Algorithms for Optimization = 31
4 BASELINE ADAPTIVE IMAGE SEGMENTATION USING A GENETIC ALGORITHM = 39
 4.1 Self - Optimizing Adaptive Image Segmentation System = 39
 4.2 Image Characteristics = 41
 4.3 Image Distance Measure = 44
 4.4 Genetic Learning System = 46
 4.5 Image Segmentation Algorithm = 50
 4.6 Global and Local Segmentation Evaluation = 52
 4.7 Adaptive Image Segmentation Algorithm = 58
5 BASIC EXPERIMENTAL RESULTS - INDOOR IMAGERY = 61
 5.1 Indoor Imagery Experiment = 61
 5.2 Training Experiment = 76
 5.3 Testing Experiment = 96
 5.4 Comparison of the Adaptive Image Segmentation with Other Techniques in Computer Vision = 106
6 BASIC EXPERIMENTAL RESULTS - OUTDOOR IMAGERY = 109
 6.1 Outdoor Imagery Experiments = 109
 6.2 Training Experiments = 133
 6.3 Testing Experiments = 155
 6.4 Comparison of the Adaptive Image Segmentation with Other Techniques in Computer Vision = 177
7 EVALUATING THE EFFECTIVENESS OF THE BASELINE TECHNIQUE - FURTHER EXPERIMENTS = 183
 7.1 Comparison of the Adaptive System with Random Search = 183
 7.2 Effectiveness of the Reproduction and Crossover Operators = 186
 7.3 Demonstration of the Learning Behavior = 188
8 HYBRID SEARCH SCHEME FOR ADAPTIVE IMAGE SEGMENT = 195
 8.1 Integrating Genetic Algorithm and Hill Climbing = 195
 8.2 Experimental Results = 199
9 SIMULTANEOUS OPTIMIZATION OF GLOBAL AND LOCAL EVALUATION MEASURES = 215
 9.1 Multiobjective Optimization with Genetic Algorithm = 216
 9.2 Adaptive Image Segmentation Using Multiobjective Optimization = 218
 9.3 Experimental Results = 220
10 SUMMARY = 255
REFERENCES = 261
INDEX = 269