Image Operators: Image Processing in Python (Hardcover)

PART I Python. Python and Images. Useful Tools. Numpy and Scipy. Python Image Library (PIL). Additional Library of Generic Tools. Differences in Images and Matrices. Summary. 2 The Image Dancer [Included software for interactive viewing of images] 3 Images with Scipy [Image input, output and rudimentary manipulation using SciPy]. Reading and Writing Images. Viewing an Image. Image Manipulations [Scripts for the simplest operations]. Resizing an Image. Shifting an Image. Rotating an Image. Binary Operations. Images and PIL [Similar content to using Python Image Library]. Reading and Writing Images. Selected Image Functions. Copy, Crop and Paste. Rotation. 4. Blending. Image Conversions [Converting between formats with a forward link to the digital image chapter]. Histograms. Summary. PART II Digital Images. Operator Nomenclature [Introduction to Operator Notation]. 5. Image Representation. Operator Symbol [Representing selected components of the previous chapters such as rotation, shift, blend in operator notation.]. Types of Operators [Classification system for the operators]. Creation Operators [Those that create images or a set of images]. Informational Operators [Those that provide information but do not manipulate the image]. Intensity Operators [Those that modify the pixel intensities but leave the spatial information unchanged]. Geometric Operators [Operators that change the spatial information but leave the intensity information unchanged]. Expansion Operators [Operators that expand the dimensionality of the images while reducing the complexity of the images]. Coordinate Operators [Those that convert images from one coordinate system to another]. Channel Operators [Those that work on the different channels in an image ? particularly with color models]. Examples [Selected examples of common image processing protocols that may combine operators from different classes]. 6 Digital Image Formats [Explanations of the features of popular image formats including loss of information during compression]. Bitmaps. JPEG. GIF. TIFF [Includes alterations in uncompressed formats]. PNG. Resolution [both intensity resolution and spatial resolution]. Summary. 7 Image Space Noise. Theory [Noise that is represented in Image space]. Erosion and Dilation. Intensity Smoothing. Summary. 8 Color. [Popular color models and their justification. Includes SciPy Conversions]. RGB. HSV Family. YUV Family. C*I*E* LAB. Multispectral Images [Brief explanation of multi- and hyper-spectral images]. Summary. PART III Image Space Operations. 9 Edge Detection and Enhancement. Edges and Derivatives. Sobel Filters. Difference of Gaussians. Summary. 10 Geometric Transformations. Linear Transformations [linear, shift, non integer shifts]. Rotations [including loss of information]. Dilation and Erosion [Revisited for non-noise applications]. Polar Transformations. Pincushion and Barrel Transformations. Miscellaneous Transformations [Geometric, affine, coordinate, transformations]. Summary. 11 Hough Transformation. Linear Hough. Circular Hough [With a forward link to correlations]. 12 Wavelets. Theory. Wavelet Decomposition. 13 Eigen Images. 6. Justification. Eigenvectors and Eigenvalues [quick review of mathematics]. Principal Component Analysis [Including some details on the covariance matrix. This section will include the Python implementation]. Eigen images [Including Turk & Pentland theory, Python implementation, an example in face recognition]. Natural Eigen images. Summary. 14 Corners [Methods in detection and enhancement of Corners]. Theory. Harris Detectors. Examples. Summary. 15 Empirical Mode Decomposition (EMD). Theory and Implementation in 1D. Theory and Implementation in 2D. Summary. PART IV Fourier Space. 16 Fourier Analysis. Theory. Digital Fourier Transform [Including properties, Python implementation and the Fast Fourier Transform]. Fourier Transforms in Higher Dimensions [Including Python implementation]. The Swapping Function. Examples with Simple Geometric Shapes [to show the reader where the information is insider of the Fourier space]. 17 Filtering [Using Fourier transforms]. Hi-pass and Lo-Pass Filters. Windowing Functions. Band Pass and Wedge Filters [Filtering objects according to size or orientation]. The Wrap Around Effect. Summary. 18 Correlations [Using correlations or convolutions in image processing]. Theory. Small Kernel Applications[Correlating a large image with a small kernel]. Computations in Fourier Space [Theory to perform correlations in Fourier Space]. Example. Composite Filtering [SDF, Mace and Fractional power composite filters. Also includes dual filters]. Restrictions in Correlations [What correlations cannot do]. Summary. 19 Noise. Image Space Noise [Revisited from earlier chapter, Additional material includes Gaussian noise]. Colored Noise. Structured Noise [regular patterns of noise embedded in the image]. 7 Other Types of Noise. Methods for Noise Reduction [smoothing, lo-pass filters, wavelets, EMD, Erosion and Dilation. Summary. 20 Gabor Filtering. Theory [restricted to image space theory]. Fourier Based Theory. Example. Summary. 21 Fingerprint Images [A chapter dedicated to fingerprints since they are unique in that the information is frequency and flow instead of spatial and intensities]. Classes [whorl, loop, arch]. Wedge Filtering. Standard Filtering [Mostly work by AK Jain]. Flow Mapping [representing the flow of the ridges]. Summary. PART V Texture and Shape. 22 Texture. Statistical Methods [Texture classification using only local statistics]. Edge Based Methods [Edge density]. Wavelet Based Methods. Filter Based Methods [Law's Filters, Gabor Filters]. GLCM. 23 Shape Detection. Fourier Descriptors. Medial Axes. Level Sets. Shape Deformation. PART VI Basis Sets. 24 Basis Sets [presenting the idea that most expansion algorithms are part of a larger family of basis sets. 25 Pulse Images. Pulse-Coupled Neural Networks. Auto waves [Waves that do not reflect or refract that are inherent in the PCNN communications, includes interference within the PCNN model]. Intersecting Cortical Model [A reduced model with superior performance to the PCNN]. Texture Classification Examples. Summary. 26 Clustering [It is necessary to review clustering algorithms before the next chapter]. Justification. k-Means. Self-Organizing Maps. Neural Networks. Segmentation Example [Image segmentation example]. Summary. 8. 27 Content Based Image Retrieval [Review of some methods and implementation in Python]. PART VII Appendix. 28 Operator Tables.