Muutke küpsiste eelistusi

Image Operators: Image Processing in Python [Kõva köide]

3.00/5 (2 hinnangut Goodreads-ist)
(George Mason University, Fairfax, VA USA)
  • Formaat: Hardback, 366 pages, kõrgus x laius: 254x178 mm, kaal: 878 g, 36 Illustrations, color; 275 Illustrations, black and white
  • Ilmumisaeg: 24-Oct-2018
  • Kirjastus: CRC Press Inc
  • ISBN-10: 1498796184
  • ISBN-13: 9781498796187
Teised raamatud teemal:
Image Operators: Image Processing in PythonSuurem pilt
  • Formaat: Hardback, 366 pages, kõrgus x laius: 254x178 mm, kaal: 878 g, 36 Illustrations, color; 275 Illustrations, black and white
  • Ilmumisaeg: 24-Oct-2018
  • Kirjastus: CRC Press Inc
  • ISBN-10: 1498796184
  • ISBN-13: 9781498796187
Teised raamatud teemal:
Püsilink: https://www.kriso.ee/db/9781498796187.html
Märksõnad:
For decades, researchers have been developing algorithms to manipulate and analyze images. From this, a common set of image tools now appear in many high-level programming languages. Consequently, the amount of coding required by a user has significantly lessened over the years. While the libraries for image analysis are coalescing to a common toolkit, the language of image analysis has remained stagnant. Often, textual descriptions of an analytical protocol consume far more real estate than does the computer code required to execute the processes. Furthermore, the textual explanations are sometimes vague or incomplete. This book offers a precise mathematical language for the field of image processing. Defined operators correspond directly to standard library routines, greatly facilitating the translation between mathematical descriptions and computer script. This text is presented with Python 3 examples.





This text will provide a unified language for image processing





Provides the theoretical foundations with accompanied Python® scripts to precisely describe steps in image processing applications





Linkage between scripts and theory through operators will be presented





All chapters will contain theories, operator equivalents, examples, Python® codes, and exercises
Python Codes xv
Preface xxi
Software and Data xxiii
Author xxv
Part I Image Operators
Chapter 1 Introduction
3(4)
1.1 Scripting in Python
3(1)
1.2 Installation
4(3)
1.2.1 Example Codes
4(1)
1.2.2 Establishing a Work Space
4(1)
1.2.3 The Spyder Interface
5(1)
1.2.4 Intent of the Text
5(2)
Chapter 2 Operator Nomenclature
7(14)
2.1 Image Notation
7(1)
2.2 Operators
8(10)
2.2.1 Creation Operators
8(1)
2.2.2 Channel Operators
9(3)
2.2.3 Informational Operators
12(2)
2.2.4 Intensity Operators
14(2)
2.2.5 Geometric Operators
16(1)
2.2.6 Transformation Operators
16(1)
2.2.7 Expansion Operators
17(1)
2.3 Combinations and Reduced Notation
18(1)
2.4 Summary
19(2)
Chapter 3 Scripting in Python
21(38)
3.1 Basic Python Skills
21(2)
3.1.1 Variables
21(1)
3.1.2 Strings
22(1)
3.1.3 Type Conversions with Strings
23(1)
3.2 Tuples, List, Dictionaries, and Sets
23(3)
3.2.1 Tuple
23(1)
3.2.2 Slicing
23(2)
3.2.3 Lists
25(1)
3.2.4 Dictionaries
25(1)
3.2.5 Sets
26(1)
3.3 Flow Control
26(6)
3.3.1 The if Command
27(1)
3.3.2 The while Command
28(1)
3.3.3 Break and Continue
29(1)
3.3.4 The For Loop
29(2)
3.3.5 The map and lambda Functions
31(1)
3.3.6 Image Operators and Control
31(1)
3.4 Input and Output
32(1)
3.4.1 Reading and Writing Text Files
32(1)
3.4.2 Pickling Files
32(1)
3.5 Defining Functions
33(3)
3.5.1 Function Components
33(1)
3.5.2 Returns
34(1)
3.5.3 Default Arguments
35(1)
3.5.4 Function Help
35(1)
3.6 Modules
36(2)
3.7 Errors
38(1)
3.8 NumPy
39(13)
3.8.1 Creating Arrays
39(3)
3.8.1.1 Zeros and Ones
39(1)
3.8.1.2 Random
40(1)
3.8.1.3 Geometric Shapes
41(1)
3.8.1.4 Conversion of Numerical Data
41(1)
3.8.2 Manipulating Arrays
42(9)
3.8.2.1 Display Option
42(1)
3.8.2.2 Converting Arrays
42(1)
3.8.2.3 Simple Math
42(1)
3.8.2.4 Multiplying Vectors
43(1)
3.8.2.5 Multiplying Matrices
44(1)
3.8.2.6 Array Functions
44(3)
3.8.2.7 Decisions
47(1)
3.8.2.8 Advanced Slicing
48(1)
3.8.2.9 Universal Functions
48(1)
3.8.2.10 Sorting
49(2)
3.8.3 Indices
51(1)
3.9 SciPy
52(4)
3.9.1 Loading and Saving Images
53(1)
3.9.2 Examples from ndimage
54(5)
3.9.2.1 Rotation and Shift
54(1)
3.9.2.2 Center of Mass
55(1)
3.10 Summary
56(3)
Chapter 4 Digital Images
59(8)
4.1 Images in Python
59(1)
4.2 Resolution
59(4)
4.2.1 Intensity Resolution
59(2)
4.2.2 Spatial Resolution
61(2)
4.3 Digital Formats
63(2)
4.3.1 Bitmaps
63(1)
4.3.2 JPEG
63(1)
4.3.3 GIF
63(1)
4.3.4 TIFF
64(1)
4.3.5 PNG
65(1)
4.3.6 Other Compressions
65(1)
4.4 Summary
65(2)
Chapter 5 Color
67(14)
5.1 The RGB Color Model
67(2)
5.2 The HSV Color Model
69(3)
5.3 The YUV Family
72(1)
5.4 CIE L*a*b*
73(1)
5.5 Improvements in Recognition
74(3)
5.6 Summary
77(4)
Part II Image Space Manipulations
Chapter 6 Geometric Transformations
81(20)
6.1 Selections
81(2)
6.2 Linear Translation
83(2)
6.2.1 Simple Shifting
83(1)
6.2.2 NonInteger Shifts
84(1)
6.3 Scaling
85(2)
6.4 Rotation
87(1)
6.5 Dilation and Erosion
88(2)
6.6 Coordinate Mapping
90(1)
6.7 Polar Transformations
90(5)
6.7.1 Theory
91(1)
6.7.2 Python Implementation
92(2)
6.7.3 Example
94(1)
6.8 Pincushion and Barrel Transformations
95(1)
6.9 Other Transformations
96(3)
6.9.1 Generic Transformations
97(1)
6.9.2 Affine Transformation
98(1)
6.10 Summary
99(2)
Chapter 7 Image Morphing
101(10)
7.1 Warp
101(5)
7.1.1 Marking Fiducial Points
101(1)
7.1.2 Image Dancer
101(2)
7.1.3 Delaunay Tessellation
103(1)
7.1.4 Applying the Warp
104(2)
7.2 Average Face
106(1)
7.3 Image Morphing
107(4)
Chapter 8 Principle Component Analysis
111(16)
8.1 The Purpose of PCA
111(1)
8.2 Covariance Matrix
111(1)
8.3 Eigenvectors
112(1)
8.4 PCA
113(11)
8.4.1 Distance Tests
116(1)
8.4.2 Organization Example
116(5)
8.4.3 RGB Example
121(3)
8.5 First Order Nature of PCA
124(1)
8.6 Summary
124(3)
Chapter 9 Eigenimages
127(10)
9.1 Eigenimages
127(10)
9.1.1 Large Covariance Matrix
128(1)
9.1.2 Python Implementation
128(2)
9.1.3 Face Recognition Example
130(1)
9.1.4 Natural Eigenimages
131(6)
Part Ill Frequency Space Manipulations
Chapter 10 Image Frequencies
137(16)
10.1 Complex Numbers
137(1)
10.2 Theory
138(1)
10.3 Digital Fourier Transform
138(2)
10.3.1 FFT in Python
139(1)
10.3.2 Signal Reconstruction
139(1)
10.4 Properties of a Fourier Transform
140(4)
10.4.1 DC Term
140(1)
10.4.2 Conservation of Energy
141(1)
10.4.3 Replication
142(1)
10.4.4 Addition
142(1)
10.4.5 Shift
143(1)
10.4.6 Scale
143(1)
10.4.7 Power Spectrum
144(1)
10.5 Displaying the Transform
144(1)
10.6 Simple Shapes
145(2)
10.6.1 Rectangle
145(1)
10.6.2 Circle
146(1)
10.7 Frequency Bands
147(2)
10.8 Windowing
149(3)
10.9 Summary
152(1)
Chapter 11 Filtering in Frequency Space
153(12)
11.1 Frequency Filtering
153(3)
11.1.1 Low-pass Filter
153(1)
11.1.2 High-pass Filter
154(1)
11.1.3 Band-pass Filter
155(1)
11.2 Directional Filtering
156(2)
11.3 Fingerprint Example
158(2)
11.4 Artifact Removal
160(3)
11.5 Summary
163(1)
11.6 Problems
163(2)
Chapter 12 Correlations
165(24)
12.1 Justification and Theory
165(1)
12.2 Theory
165(2)
12.2.1 Computations in Fourier Space
166(1)
12.3 Implementation in Python
167(7)
12.3.1 Brute Force
167(1)
12.3.2 Method Based on Fourier Transforms
168(1)
12.3.3 Example - Geometric Shapes
169(1)
12.3.4 Example - Boat Isolation
170(4)
12.4 Composite Filtering
174(1)
12.5 SDF and MACE
175(9)
12.5.1 Fractional Power Filter (FPF)
176(36)
12.5.1.1 Theory
176(1)
12.5.1.2 Manipulating a
177(1)
12.5.1.3 Example
178(2)
12.5.1.4 The Constraints
180(2)
12.5.1.5 Dual FPFs
182(2)
12.6 Restrictions of Correlations
184(1)
12.7 Summary
184(5)
Part IV Texture and Shape
Chapter 13 Edge Detection
189(10)
13.1 Edges
189(1)
13.2 The Sobel Filters
190(1)
13.3 Difference of Gaussians
191(2)
13.4 Corners
193(6)
Chapter 14 Hough Transforms
199(10)
14.1 Detection of a Line
199(3)
14.2 Detection of a Circle
202(2)
14.3 Application
204(1)
14.4 Summary
205(4)
Chapter 15 Noise
209(12)
15.1 Random Noise
209(1)
15.2 Salt and Pepper Noise
209(3)
15.3 Camera Noise
212(1)
15.4 Colored Noise
212(1)
15.5 Comparison of Noise Removal Systems
212(5)
15.5.1 Smoothing
213(1)
15.5.2 Low-Pass Filtering
214(1)
15.5.3 Erosion and Dilation
214(1)
15.5.4 Median Filter
215(1)
15.5.5 Wiener Filter
216(1)
15.6 Other Types of Noise
217(1)
15.7 Summary
217(4)
Chapter 16 Texture Recognition
221(22)
16.1 Data
221(1)
16.2 Edge Density
221(17)
16.2.1 Statistical Method
221(2)
16.2.2 The Method of Rosenfeld and Thurston
223(4)
16.2.3 Wavelet Decomposition and Texture
227(3)
16.2.4 Gray-Level Co-Occurrence Matrix
230(8)
16.2.4.1 Angular Second Moment
232(1)
16.2.4.2 Contrast
232(1)
16.2.4.3 Correlation
233(1)
16.2.4.4 Variance
234(1)
16.2.4.5 Entropy
234(1)
16.2.4.6 The Remaining Haralick Metrics
235(3)
16.3 Filter-Based Methods
238(2)
16.3.1 Law's Filters
238(2)
16.4 Summary
240(3)
Chapter 17 Gabor Filtering
243(8)
17.1 Gabor Filtering
243(2)
17.2 Edge Response
245(1)
17.3 Texture Extraction with Gabor Filters
246(3)
17.4 Gabor Filters in Fourier Space
249(1)
17.5 Summary
249(2)
Chapter 18 Describing Shape
251(24)
18.1 Contour Methods
251(11)
18.1.1 Chain Code
251(1)
18.1.2 The Polygon Method
252(1)
18.1.3 Metrics Used to Describe Shape
252(3)
18.1.4 Fourier Descriptors
255(3)
18.1.5 Wavelets
258(1)
18.1.6 Elastic Matching
258(4)
18.2 Region Methods
262(5)
18.2.1 Eigenvectors and Eigenvalues
262(3)
18.2.2 Shape Metrics
265(2)
18.3 Describing Structure
267(4)
18.3.1 Curvature Flow
267(2)
18.3.2 Medial Axis
269(2)
18.4 Problems
271(4)
Part V Basis
Chapter 19 Basis Sets
275(18)
19.1 Discrete Cosine Transform
276(3)
19.2 Zernike Polynomials
279(3)
19.3 Empirical Mode Decomposition
282(3)
19.4 Image Analysis with Basis Sets
285(8)
Chapter 20 Pulse Images and Autowaves
293(10)
20.1 Pulse-Coupled Neural Network
293(3)
20.1.1 Mammalian Visual Cortex
293(1)
20.1.2 PCNN
293(3)
20.1.2.1 Theory
294(1)
20.1.2.2 Pulse Streams
294(1)
20.1.2.3 Applications
295(1)
20.1.2.4 Operator Notation
296(1)
20.2 Intersecting Cortical Model
296(2)
20.2.1 Centripetal Autowaves
297(1)
20.2.2 ICM
297(1)
20.3 Texture Classification with the ICM
298(2)
20.4 Summary
300(3)
Appendix A Operators 303(22)
Appendix B Operators in Symbolic Order 325(2)
Appendix C Lengthy Codes 327(6)
Bibliography 333(2)
Index 335
Jason M Kinser, DSc, has been an associate professor at George Mason University for more than 18 years teaching courses in physics, computational science, bioinformatics and forensic science. Recently, he converted the traditional university physics course into an active learning technology environment at GMU. His research interests include modern teaching techniques, more effective methods in text-based education, image operators and analysis, pulse image processing and multi-domain data analysis. This book was born from a desire to engage students in physics education and to find ways of reducing the external costs that both students and institutions incur within the traditional education framework.Jason M Kinser, DSc, has been an associate professor at George Mason University for more than 18 years teaching courses in physics, computational science, bioinformatics and forensic science. Recently, he converted the traditional university physics course into an active learning technology environment at GMU. His research interests include modern teaching techniques, more effective methods in text-based education, image operators and analysis, pulse image processing and multi-domain data analysis. This book was born from a desire to engage students in physics education and to find ways of reducing the external costs that both students and institutions incur within the traditional education framework.