Feature Extraction and Image Processing for Computer Vision, Fifth Edition is an essential guide to the implementation of image processing and computer vision techniques, with tutorial introductions and sample code in MATLAB and Python. Algorithms are presented and fully explained to enable complete understanding of the methods and techniques demonstrated, providing a link between theory and implementation. Essential background theory is carefully explained. This text gives students and researchers in image processing and computer vision a complete introduction to classic and state-of-the art methods in feature extraction together with practical guidance on their implementation.
1. Chapter 1. Introduction∗ - p. 1 2. Chapter 2. Images, sampling and frequency-domain processing∗ - p. 33 3. 2.1 Overview - p. 33 4. 2.2 Image formation - p. 33 5. 2.3 The Fourier transform - p. 36 6. 2.4 The sampling criterion - p. 43 7. 2.5 The discrete Fourier transform - p. 47 8. 2.6 Properties of the Fourier transform - p. 59 9. 2.7 Transforms other than Fourier - p. 64 10. 2.8 Applications using frequency-domain properties - p. 75 11. 2.9 Further reading - p. 77 12. Chapter 3. Image processing∗ - p. 81 13. Chapter 4. Distance, classification and deep learning∗ - p. 123 14. 4.1 Overview - p. 123 15. 4.2 Basis of classification and learning - p. 123 16. 4.3 Distance measures - p. 127 17. 4.4 Classification - p. 137 18. 4.5 Neural networks - p. 145 19. 4.6 Deep learning - p. 163 20. 4.7 Image segmentation with deep learning - p. 194 21. 4.8 Further reading - p. 207 22. Chapter 5. Low-level feature extraction (including edge detection)∗ - p. 213 23. 5.1 Overview - p. 213 24. 5.2 Edge detection - p. 215 25. 5.3 Phase congruency - p. 248 26. 5.4 Localised feature extraction/detection - p. 254 27. 5.5 Describing image motion - p. 280 28. 5.6 Further reading - p. 299 29. Chapter 6. High-level feature extraction: Fixed shape analysis∗ - p. 305 30. 6.1 Overview - p. 305 31. 6.2 Segmenting objects from images - p. 307 32. 6.3 Feature extraction by low level features - p. 315 33. 6.4 Feature extraction by shape - p. 327 34. 6.5 Hough Transform (HT) - p. 344 35. 6.6 Further reading - p. 384 36. Chapter 7. High-level feature extraction: Deformable shape analysis∗ - p. 391 37. 7.1 Overview - p. 391 38. 7.2 Deformable shape analysis - p. 391 39. 7.3 Active contours (snakes) - p. 396 40. 7.4 Shape skeletonisation - p. 421 41. 7.5 Flexible shape models – active shape and active appearance - p. 431 42. 7.6 Further reading - p. 435 43. Chapter 8. Object description∗ - p. 441 44. 8.1 Overview and invariance requirements - p. 441 45. 8.2 Boundary descriptions - p. 442 46. 8.3 Region descriptors - p. 469 47. 8.4 Further reading - p. 498 48. Chapter 9. Filtering/denoising and region-based analysis∗ - p. 503 49. 9.1 Overview - p. 503 50. 9.2 Advanced denoising operators and image super-resolution - p. 503 51. 9.3 Region-based analysis - p. 525 52. 9.4 Texture description and analysis - p. 537 53. 9.5 Further reading - p. 555 54. Chapter 10. Moving object detection, description and tracking∗ - p. 561 55. 10.1 Overview - p. 561 56. 10.2 Moving object detection - p. 561 57. 10.3 Tracking moving features - p. 577 58. 10.4 Moving feature extraction and description - p. 598 59. 10.5 Further reading - p. 608 60. Chapter 11. Camera geometry fundamentals∗ - p. 615 61. Chapter 12. Colour images∗ - p. 643 62. 12.1 Overview - p. 643 63. 12.2 Colour image theory - p. 644 64. 12.3 Perception-based colour models: CIE RGB and CIE XYZ - p. 649 65. 12.4 Additive and subtractive colour models - p. 668 66. 12.5 Luminance and chrominance colour models - p. 674 67. 12.6 Additive perceptual colour models - p. 682 68. 12.7 More colour models - p. 696 69. Index - p. 699
Feature Extraction and Image Processing for Computer Vision, Fifth Edition is an essential guide to the implementation of image processing and computer vision techniques, with tutorial introductions and sample code in MATLAB and Python. Algorithms are presented and fully explained to enable complete understanding of the methods and techniques demonstrated, providing a link between theory and implementation. Essential background theory is carefully explained. This text gives students and researchers in image processing and computer vision a complete introduction to classic and state-of-the art methods in feature extraction together with practical guidance on their implementation.
1. Chapter 1. Introduction∗ - p. 1 2. Chapter 2. Images, sampling and frequency-domain processing∗ - p. 33 3. 2.1 Overview - p. 33 4. 2.2 Image formation - p. 33 5. 2.3 The Fourier transform - p. 36 6. 2.4 The sampling criterion - p. 43 7. 2.5 The discrete Fourier transform - p. 47 8. 2.6 Properties of the Fourier transform - p. 59 9. 2.7 Transforms other than Fourier - p. 64 10. 2.8 Applications using frequency-domain properties - p. 75 11. 2.9 Further reading - p. 77 12. Chapter 3. Image processing∗ - p. 81 13. Chapter 4. Distance, classification and deep learning∗ - p. 123 14. 4.1 Overview - p. 123 15. 4.2 Basis of classification and learning - p. 123 16. 4.3 Distance measures - p. 127 17. 4.4 Classification - p. 137 18. 4.5 Neural networks - p. 145 19. 4.6 Deep learning - p. 163 20. 4.7 Image segmentation with deep learning - p. 194 21. 4.8 Further reading - p. 207 22. Chapter 5. Low-level feature extraction (including edge detection)∗ - p. 213 23. 5.1 Overview - p. 213 24. 5.2 Edge detection - p. 215 25. 5.3 Phase congruency - p. 248 26. 5.4 Localised feature extraction/detection - p. 254 27. 5.5 Describing image motion - p. 280 28. 5.6 Further reading - p. 299 29. Chapter 6. High-level feature extraction: Fixed shape analysis∗ - p. 305 30. 6.1 Overview - p. 305 31. 6.2 Segmenting objects from images - p. 307 32. 6.3 Feature extraction by low level features - p. 315 33. 6.4 Feature extraction by shape - p. 327 34. 6.5 Hough Transform (HT) - p. 344 35. 6.6 Further reading - p. 384 36. Chapter 7. High-level feature extraction: Deformable shape analysis∗ - p. 391 37. 7.1 Overview - p. 391 38. 7.2 Deformable shape analysis - p. 391 39. 7.3 Active contours (snakes) - p. 396 40. 7.4 Shape skeletonisation - p. 421 41. 7.5 Flexible shape models – active shape and active appearance - p. 431 42. 7.6 Further reading - p. 435 43. Chapter 8. Object description∗ - p. 441 44. 8.1 Overview and invariance requirements - p. 441 45. 8.2 Boundary descriptions - p. 442 46. 8.3 Region descriptors - p. 469 47. 8.4 Further reading - p. 498 48. Chapter 9. Filtering/denoising and region-based analysis∗ - p. 503 49. 9.1 Overview - p. 503 50. 9.2 Advanced denoising operators and image super-resolution - p. 503 51. 9.3 Region-based analysis - p. 525 52. 9.4 Texture description and analysis - p. 537 53. 9.5 Further reading - p. 555 54. Chapter 10. Moving object detection, description and tracking∗ - p. 561 55. 10.1 Overview - p. 561 56. 10.2 Moving object detection - p. 561 57. 10.3 Tracking moving features - p. 577 58. 10.4 Moving feature extraction and description - p. 598 59. 10.5 Further reading - p. 608 60. Chapter 11. Camera geometry fundamentals∗ - p. 615 61. Chapter 12. Colour images∗ - p. 643 62. 12.1 Overview - p. 643 63. 12.2 Colour image theory - p. 644 64. 12.3 Perception-based colour models: CIE RGB and CIE XYZ - p. 649 65. 12.4 Additive and subtractive colour models - p. 668 66. 12.5 Luminance and chrominance colour models - p. 674 67. 12.6 Additive perceptual colour models - p. 682 68. 12.7 More colour models - p. 696 69. Index - p. 699
