Index

A

• active contours / Active contours, morphological snakes, and GrabCut algorithms, Active contours
• active contours model / Active contours
• Adam optimizer / Classification with dense FC layers with Keras
• aliasing / Down-sampling
• anti-aliasing / Down-sampling and anti-aliasing, Image pyramids (Gaussian and Laplacian) – blending images
• artificial neural network (ANN) / What is deep learning?
• Atrous Spatial Pyramid Pooling (ASPP) / DeepLab V3+

B

• band-stop (notch) filter
  • about / Band-stop (notch) filter
  • used, to remove periodic noise from images / Using a notch filter to remove periodic noise from images
• Beier-Neely morphing / Face morphing
• bilateral filter
  • using / Using the bilateral filter
• binary operations
  • erosion / Erosion
  • dilation / Dilation
  • opening and closing / Opening and closing
  • skeletonizing / Skeletonizing
  • convex hull, computing / Computing the convex hull
  • small objects function, removing / Removing small objects
  • white top-hat / White and black top-hats
  • black top-hat / White and black top-hats
  • boundary, extracting / Extracting the boundary 
  • fingerprint cleaning, with opening and closing / Fingerprint cleaning with opening and closing
  • grayscale operations / Grayscale operations
• black top-hat / White and black top-hats
• Blob detectors
  • with LoG / Blob detectors with LoG, DoG, and DoH
  • with DoG / Blob detectors with LoG, DoG, and DoH
  • with DoH / Blob detectors with LoG, DoG, and DoH
• blurred version / Unsharp masking
• BoundingBoxes
  • computing, with HOG-SVM / Computing BoundingBoxes with HOG-SVM

C

• canny edge detector
  • with scikit-image / The Canny edge detector with scikit-image
• closing / Opening and closing
• color palette / K-means clustering for image segmentation with color quantization
• Compact Watershed algorithm / Felzenszwalb, SLIC, QuickShift, and Compact Watershed algorithms , Compact Watershed
• contrast stretching
  • about / Contrast stretching
  • PIL, used as point operation / Using PIL as a point operation
  • PIL ImageEnhance module, used / Using the PIL ImageEnhance module
  • with scikit-image / Contrast stretching and histogram equalization with scikit-image
• convex hull
  • computing / Computing the convex hull
  • about / Computing the convex hull
• convolution
  • about / Understanding convolution
  • on image / Why convolve an image?
  • with SciPy signal module's convolve2d() function / Convolution with SciPy signal's convolve2d
  • applying, to grayscale image / Applying convolution to a grayscale image
  • boundary conditions / Convolution modes, pad values, and boundary conditions
  • modes / Convolution modes, pad values, and boundary conditions
  • pad values / Convolution modes, pad values, and boundary conditions
  • applying, to color (RGB) image / Applying convolution to a color (RGB) image
  • with SciPy ndimage.convolve / Convolution with SciPy ndimage.convolve
  • versus correlation / Correlation versus convolution
  • template, matching with cross-correlation between image / Template matching with cross-correlation between the image and template
• convolutional neural networks (CNN)
  • about / CNNs, Some popular deep CNNs
  • architecture / Conv or pooling or FC layers – CNN architecture and how it works
  • working / Conv or pooling or FC layers – CNN architecture and how it works
  • convolutional layer / Convolutional layer
  • pooling layer / Pooling layer
  • non-linearity / Non-linearity – ReLU layer
  • FC layer / FC layer
  • dropout / Dropout
  • classifying, with Keras / CNN for classification with Keras
  • MNIST, classifying / Classifying MNIST
  • intermediate layers, visualizing / Visualizing the intermediate layers 
  • VGG-16/19 / VGG-16/19
  • InceptionNet / InceptionNet
  • Residual Network (ResNet) / ResNet
• convolution theorem
  • about / Convolution theorem and frequency domain Gaussian blur
  • application / Application of the convolution theorem

D

• 2D projection / 2D projection and visualization
• 2D visualization / 2D projection and visualization
• DC coefficient / Plotting the frequency spectrum
• deconvolution / Deconvolution and inverse filtering with FFT
• DeepLab V3+
  • used, for deep semantic segmentation / Deep semantic segmentation with DeepLab V3+
  • about / DeepLab V3+
  • architecture / DeepLab v3 architecture
  • model, used for semantic segmentation / Steps you must follow to use DeepLab V3+ model for semantic segmentation
• deep learning
  • in image processing / Deep learning in image processing
  • about / What is deep learning?, Why deep learning?
  • versus classical / Classical versus deep learning
• deep semantic segmentation
  • with DeepLab V3+ / Deep semantic segmentation with DeepLab V3+
  • semantic segmentation / Semantic segmentation
• degradation / Image restoration
• derivatives / Derivatives and gradients
• descriptors
  • versus feature detectors / Feature detectors versus descriptors
• Determinant of Hessian (DoH) / Determinant of Hessian (DoH)
• Difference of Gaussian (DoG) / Band-pass filter (BPF) with DoG, Difference of Gaussian (DoG)
• dilation / Dilation
• Discrete Cosine Transform (DCT) / Why do we need the DFT?
• Discrete Fourier Transform (DFT)
  • about / Discrete Fourier Transform
  • need for / Why do we need the DFT?
  • computing, Fast Fourier Transform (FFT) algorithm / The Fast Fourier Transform algorithm to compute the DFT
• DoG filters / The LoG and DoG filters
• down-sampling, image formation
  • anti-aliasing / Down-sampling and anti-aliasing

E

• edge-based segmentation / Edges-based/region-based segmentation, Edge-based segmentation
• edge detection
  • derivatives, used / Edge detection using derivatives and filters (Sobel, Canny, and so on)
  • filters, used / Edge detection using derivatives and filters (Sobel, Canny, and so on)
  • gradient magnitude computed, with partial derivatives / With gradient magnitude computed using the partial derivatives
  • with scikit-image / Different edge detectors with scikit-image – Prewitt, Roberts, Sobel, Scharr, and Laplace
  • Hildreth's algorithm, zero-crossing computation / Edge detection with the Marr and Hildreth's algorithm using the zero-crossing computation
  • Marr algorithm, zero-crossing computation / Edge detection with the Marr and Hildreth's algorithm using the zero-crossing computation
• edges
  • enhancing, with PIL / Finding and enhancing edges with PIL
  • finding, with PIL / Finding and enhancing edges with PIL
• eigenfaces
  • about / PCA and eigenfaces , Eigenfaces
  • with PCA / Eigenfaces with PCA
  • reconstruction / Reconstruction
  • decomposition / Eigen decomposition
• entropy / Computing the local entropy
• erosion / Erosion

F

• face morphing / Face morphing
• Fast Fourier Transform (FFT)
  • about / The Fast Fourier Transform algorithm to compute the DFT
  • with scipy.fftpack module / The FFT with the scipy.fftpack module
  • frequency spectrum, plotting / Plotting the frequency spectrum
  • with numpy.fft module / The FFT with the numpy.fft module
  • DFT, phase / Computing the magnitude and phase of a DFT
  • magnitude, computing / Computing the magnitude and phase of a DFT
• feature detectors
  • versus descriptors / Feature detectors versus descriptors
  • about / Feature detectors versus descriptors
• feature extractors / Feature detectors versus descriptors
• Felzenszwalb algorithm
  • about / Felzenszwalb, SLIC, QuickShift, and Compact Watershed algorithms 
  • graph-based image segmentation / Felzenszwalb's efficient graph-based image segmentation
• finite differences / Derivatives and gradients
• Floyd-Steinberg dithering
  • with error diffusion / Floyd-Steinberg dithering with error diffusion
• frequency domain
  • filtering / Filtering in the frequency domain (HPF, LPF, BPF, and notch filters), What is a filter?
  • enhancement / What is a filter?
  • smoothing / What is a filter?
  • template matching / What is a filter?
  • high-pass filter (HPF) / High-Pass Filter (HPF)
  • low-pass filter (LPF) / Low-pass filter (LPF)
  • band-pass filter (BPF), with DoG / Band-pass filter (BPF) with DoG
  • band-stop (notch) filter / Band-stop (notch) filter
  • image restoration / Image restoration
• frequency domain Gaussian blur
  • about / Convolution theorem and frequency domain Gaussian blur
  • with numpy fft / Frequency domain Gaussian blur filter with numpy fft
  • with scipy signal fftconvolve() / Frequency domain Gaussian blur filter with scipy signal.fftconvolve()
• fully connected (FC) layer / Conv or pooling or FC layers – CNN architecture and how it works, Transfer learning with Keras
• fully convolutional network (FCN) / Introducing YOLO v2 

G

• Gaussian Bayes classifier
  • about / Bayes classifier (Gaussian generative model)
  • generative model, training / Training the generative model – computing the MLE of the Gaussian parameters
  • posterior probabilities, computing on test data / Computing the posterior probabilities to make predictions on test data and model evaluation
  • posterior probabilities, computing on model evaluation / Computing the posterior probabilities to make predictions on test data and model evaluation
• Gaussian kernel
  • in frequency domain / Gaussian kernel in the frequency domain
  • in 2-D plot / Gaussian kernel in the frequency domain
  • in 3-D plot / Gaussian kernel in the frequency domain
  • SciPy convolve(), runtimes comparing / Comparing the runtimes of SciPy convolve() and fftconvolve() with the Gaussian blur kernel
  • fftconvolve(), runtimes comparing / Comparing the runtimes of SciPy convolve() and fftconvolve() with the Gaussian blur kernel
• Gaussian Pyramid
  • about / Image pyramids (Gaussian and Laplacian) – blending images
  • with scikit-image transform's pyramid module / A Gaussian pyramid with scikit-image transform pyramid module
  • constructing, with scikit-image transform module's reduce function / Constructing the Gaussian Pyramid
  • images, blending / Blending images with pyramids
• generalization / Deep learning in image processing
• GoogleNet (Inception v1) / InceptionNet
• GrabCut
  • about / GrabCut with OpenCV
  • with OpenCV / GrabCut with OpenCV
• GrabCut algorithms / Active contours, morphological snakes, and GrabCut algorithms
• gradient
  • about / Image derivatives – Gradient and Laplacian, Derivatives and gradients
  • displaying, on image / Displaying the magnitude and the gradient on the same image
• gradient computation
  • noise, effects / Effects of noise on gradient computation
• gray-level quantization / What is an image and how it is stored on a computer

H

• Haar-like features
  • about / Haar-like features
  • descriptor, with scikit-image / Haar-like feature descriptor with scikit-image
  • face detection / Application – face detection with Haar-like features
  • face detection, with OpenCV using pre-trained classifiers with Haar-cascade features / Face/eye detection with OpenCV using pre-trained classifiers with Haar-cascade features
  • eye detection, with OpenCV using pre-trained classifiers with Haar-cascade features / Face/eye detection with OpenCV using pre-trained classifiers with Haar-cascade features
  • finding, for face classification with random forest ensemble classifier / Finding the most important Haar-like features for face classification with the random forest ensemble classifier
• half-toning / Half-toning
• Harris Corner Detector
  • about / Harris Corner Detector
  • with scikit-image / With scikit-image
  • with sub-pixel accuracy / With sub-pixel accuracy
  • image matching / An application – image matching
• histogram equalization
  • about / Histogram processing – histogram equalization and matching
  • with scikit-image / Contrast stretching and histogram equalization with scikit-image
• histogram matching
  • about / Histogram processing – histogram equalization and matching
  • with scikit-image / Histogram matching
  • for RGB image / Histogram matching for an RGB image
• Histogram of Oriented Gradients (HOG) / Histogram of Oriented Gradients, Detecting objects with SVM using HOG features
• HOG descriptors
  • algorithm, computing / Algorithm to compute HOG descriptors
  • computing, with scikit-image / Compute HOG descriptors with scikit-image
• HOG training / HOG training
• holes
  • filling, in binary objects / Filling holes in binary objects
• Hough transform / Hough transform – detecting lines and circles

I

• image
  • I/O, with Python / Image I/O and display with Python
  • displaying, with Python / Image I/O and display with Python
  • reading, PIL used / Reading, saving, and displaying an image using PIL
  • saving, PIL used / Reading, saving, and displaying an image using PIL
  • displaying, PIL used / Reading, saving, and displaying an image using PIL
  • correct path, providing on disk / Providing the correct path to the images on the disk
  • reading, Matplotlib used / Reading, saving, and displaying an image using Matplotlib
  • saving, Matplotlib used / Reading, saving, and displaying an image using Matplotlib
  • displaying, Matplotlib used / Reading, saving, and displaying an image using Matplotlib
  • interpolating, while matplotlib imshow displayed /
  • saving, scikit-image used / Reading, saving, and displaying an image using scikit-image
  • reading, scikit-image used / Reading, saving, and displaying an image using scikit-image
  • displaying, scikit-image used / Reading, saving, and displaying an image using scikit-image
  • reading, scipy misc used / Reading, saving, and displaying an image using scipy misc
  • saving, scipy misc used / Reading, saving, and displaying an image using scipy misc
  • displaying, scipy misc used / Reading, saving, and displaying an image using scipy misc
  • matching, with BRIEF / Application – matching images with BRIEF, SIFT, and ORB
  • matching, with SIFT / Application – matching images with BRIEF, SIFT, and ORB
  • matching, with ORB / Application – matching images with BRIEF, SIFT, and ORB
  • matching, with BRIEF binary descriptors with scikit-image / Matching images with BRIEF binary descriptors with scikit-image
  • matching, with ORB feature detector using scikit-image / Matching with ORB feature detector and binary descriptor using scikit-image
  • matching, with binary descriptor using scikit-image / Matching with ORB feature detector and binary descriptor using scikit-image
  • matching, with ORB feature detector using Brute-Force matching / Matching with ORB features using brute-force matching with python-opencv
  • matching, with python-opencv / Matching with ORB features using brute-force matching with python-opencv
  • Brute-force matching, with SIFT descriptors / Brute-force matching with SIFT descriptors and ratio test with OpenCV
  • ratio test, with OpenCV / Brute-force matching with SIFT descriptors and ratio test with OpenCV
• image classification
  • with TensorFlow / Image classification with TensorFlow or Keras
  • with Keras / Image classification with TensorFlow or Keras
• image classification, supervised machine learning
  • MNIST dataset, downloading / Downloading the MNIST (handwritten digits) dataset
  • dataset, visualizing / Visualizing the dataset
  • kNN classifier, training / Training kNN, Gaussian Bayes, and SVM models to classify MNIST 
  • Gaussian Bayes classifier / Training kNN, Gaussian Bayes, and SVM models to classify MNIST 
  • SVM model / Training kNN, Gaussian Bayes, and SVM models to classify MNIST 
• image denoising
  • with FFT / Image denoising with FFT
  • filter, in FFT / Filter in FFT
  • final image, reconstructing / Reconstructing the final image
• image derivatives
  • gradient / Image derivatives – Gradient and Laplacian
  • Laplacian / Image derivatives – Gradient and Laplacian
• image formation
  • quantization / Image formation – sampling and quantization, Quantization
  • about / Image formation – sampling and quantization
  • sampling / Sampling
  • down-sampling / Down-sampling
• image inpainting / Image inpainting
• image matching
  • about / An application – image matching
  • RANSAC algorithm, used / Robust image matching using the RANSAC algorithm and Harris Corner features
  • Harris Corner features, used / Robust image matching using the RANSAC algorithm and Harris Corner features
• image processing
  • about / What is image processing and some applications, What is image processing?
  • applications / What is image processing and some applications, Some applications of image processing
  • storing, on computer / What is an image and how it is stored on a computer
• image processing libraries
  • pip, installing / Installing pip
  • installing, in Python / Installing some image processing libraries in Python
  • Anaconda distribution, installing / Installing the Anaconda distribution
  • Jupyter Notebook, installing / Installing Jupyter Notebook
• image processing pipeline
  • about / The image processing pipeline
  • acquisition and storage / The image processing pipeline
  • memory, loading / The image processing pipeline
  • disk, saving / The image processing pipeline
  • manipulation / The image processing pipeline
  • enhancement / The image processing pipeline
  • restoration / The image processing pipeline
  • segmentation / The image processing pipeline
  • information extraction/representation / The image processing pipeline
  • image understanding/interpretation / The image processing pipeline
• image quilting
  • about / Image quilting
  • texture synthesis / Texture synthesis
  • texture transfer / Texture transfer
• image restoration
  • about / Image restoration
  • deconvolution, with FFT / Deconvolution and inverse filtering with FFT
  • inverse filtering, with FFT / Deconvolution and inverse filtering with FFT
  • image denoising, with FFT / Image denoising with FFT
• image sampling / What is an image and how it is stored on a computer
• image segmentation / What is image segmentation?
• InceptionNet / InceptionNet
• inpainting / Image inpainting
• interference / Using a notch filter to remove periodic noise from images
• Inverse Discrete Fourier Transform (IDFT) / Discrete Fourier Transform
• isotropic derivative / Laplacian

J

• Jupyter notebook
  • about / Installing Jupyter Notebook
  • references / Installing Jupyter Notebook

K

• K-means clustering
  • for image segmentation, with color quantization / K-means clustering for image segmentation with color quantization
• k-nearest neighbors (KNN) classifier
  • about / k-nearest neighbors (KNN) classifier
  • computing / Computing the nearest neighbors
  • performance, evaluating / Evaluating the performance of the classifier
• Keras
  • used, for classifying dense FC layers / Classification with dense FC layers with Keras
  • network, visualizing / Visualizing the network
  • weights, visualizing in intermediate layers / Visualizing the weights in the intermediate layers 
  • used, for classifying CNN / CNN for classification with Keras
• kernel / Understanding convolution, Convolutional layer

L

• Laplacian
  • about / Image derivatives – Gradient and Laplacian, Laplacian
  • notes / Some notes about the Laplacian
• Laplacian of Gaussian (LoG) / The LoG and DoG filters, Laplacian of Gaussian (LoG)
• Laplacian Pyramid
  • about / Image pyramids (Gaussian and Laplacian) – blending images
  • with scikit-image transform's pyramid module / A Laplacian pyramid with scikit-image transform's pyramid module
  • constructing, with scikit-image transform module's reduce function / Constructing the Gaussian Pyramid
  • image, reconstructing / Reconstructing an image only from its Laplacian pyramid
  • images, blending / Blending images with pyramids
• linear noise smoothing
  • about / Linear noise smoothing
  • with PIL / Smoothing with PIL
  • with ImageFilter.BLUR / Smoothing with ImageFilter.BLUR
  • averaging, with box blur kernel / Smoothing by averaging with the box blur kernel
  • with Gaussian blur filter / Smoothing with the Gaussian blur filter
  • comparing, with box filter / Comparing smoothing with box and Gaussian kernels using SciPy ndimage
  • Gaussian kernels, SciPy ndimage used / Comparing smoothing with box and Gaussian kernels using SciPy ndimage
• local entropy
  • computing / Computing the local entropy
• LoG-convolved image / Edge detection with the Marr and Hildreth's algorithm using the zero-crossing computation
• LoG-smoothed image / Edge detection with the Marr and Hildreth's algorithm using the zero-crossing computation
• LoG filter
  • about / The LoG and DoG filters
  • with SciPy ndimage module / The LoG filter with the SciPy ndimage module
  • used, for edge detection / Edge detection with the LoG filter
• log transform / Log transform
• low-pass filter (LPF)
  • with scipy ndimage and numpy fft / LPF with scipy ndimage and numpy fft
  • with fourier-gaussian / LPF with fourier_gaussian
  • with scipy fftpack / LPF with scipy fftpack
  • SNR changes, with frequency cutoff / How SNR changes with frequency cutoff

M

• Machine Learning (ML) / Deep learning in image processing
• magnitude
  • displaying / Displaying the magnitude and the gradient on the same image
• Maximum Likelihood Estimates (MLE) / Training the generative model – computing the MLE of the Gaussian parameters
• max pooling / Pooling layer
• median filter
  • using / Using the median filter
• MNIST
  • classifying / Classifying MNIST
• morphological (Beucher) gradient
  • computing / Computing the morphological Beucher gradient
• Morphological Active Contours without Edges (MorphACWE) / Morphological snakes
• morphological contrast enhancement / Morphological contrast enhancement
• Morphological Geodesic Active Contours (MorphGAC) / Morphological snakes
• morphological Laplace
  • computing / Computing the morphological Laplace
• morphological snakes / Active contours, morphological snakes, and GrabCut algorithms, Morphological snakes
• multiple images
  • reading / Reading and displaying multiple images at once
  • displaying / Reading and displaying multiple images at once

N

• nearest neighbor classifier / k-nearest neighbors (KNN) classifier
• neural style transfer (NST)
  • with cv2, pre-trained torch model used / Neural style transfers with cv2 using a pre-trained torch model
  • about / Neural style transfers with cv2 using a pre-trained torch model
  • algorithm / Understanding the NST algorithm
  • implementing, with transfer learning / Implementation of NST with transfer learning
  • ensuring, with content loss / Ensuring NST with content loss
  • style cost, computing / Computing the style cost
  • loss, computing / Computing the overall loss
  • with Python / Neural style transfer with Python and OpenCV
  • with OpenCV / Neural style transfer with Python and OpenCV
• noise removal
  • with median filter / Noise removal with the median filter
  • opening and closing used / Using opening and closing to remove noise
• non-local means
  • using / Using non-local means
• non-maximum suppression
  • about / With gradient magnitude computed using the partial derivatives, Non-max suppression
  • algorithm / The non-maximum suppression algorithm
• nonlinear noise smoothing
  • about / Nonlinear noise smoothing
  • with PIL / Smoothing with PIL
  • median filter, using / Using the median filter
  • max and min filter, using / Using max and min filter
  • denoising, with scikit-image / Smoothing (denoising) with scikit-image
  • with scipy ndimage / Smoothing with scipy ndimage

O

• object detection, supervised machine learning
  • face detection, with Haar-like features / Face detection with Haar-like features and cascade classifiers with AdaBoost – Viola-Jones
  • cascade classifiers, with AdaBoost / Face detection with Haar-like features and cascade classifiers with AdaBoost – Viola-Jones
  • face classification, with Haar-like feature descriptor / Face classification using the Haar-like feature descriptor
  • objects, detecting with SVM using HOG features / Detecting objects with SVM using HOG features
• opening / Opening and closing
• Otsu's method / Thresholding and Otsu's segmentation
• Otsu's segmentation / Thresholding and Otsu's segmentation

P

• padding / Convolutional layer
• partial derivatives / Derivatives and gradients
• partial differential equation (PDE) / Variational image processing
• pip
  • installing / Installing pip
  • about / Installing pip
• pip installation
  • reference link / Installing pip
• pixel (pel) / What is an image and how it is stored on a computer
• point-wise intensity transformations
  • about / Point-wise intensity transformations – pixel transformation
  • log transform / Log transform
  • power-law transform / Power-law transform
  • contrast stretching / Contrast stretching
  • thresholding / Thresholding
• poisson image editing / Seamless cloning and Poisson image editing
• power-law transform / Power-law transform
• Principal Component Analysis (PCA)
  • about / PCA and eigenfaces 
  • dimension reduction / Dimension reduction and visualization with PCA
  • visualization / Dimension reduction and visualization with PCA
• pyvenv
  • reference link / Installing pip

Q

• quantization
  • about / Quantization
  • with PIL / Quantizing with PIL
• QuickShift algorithm / Felzenszwalb, SLIC, QuickShift, and Compact Watershed algorithms , QuickShift

R

• region-based segmentation
  • about / Edges-based/region-based segmentation, Region-based segmentation
  • morphological watershed algorithm / Morphological watershed algorithm
• Region Adjacency Graph (RAG) / RAG merging
• Region Of Interest (ROI) / Face classification using the Haar-like feature descriptor
• Residual Network (ResNet) / ResNet

S

• same padding / Convolutional layer
• sampling, image formation
  • up-sampling / Up-sampling, Up-sampling and interpolation 
  • interpolation / Up-sampling and interpolation 
• scale-invariant feature transform (SIFT)
  • about / Scale-invariant feature transform
  • images, matching with BRIEF / Application – matching images with BRIEF, SIFT, and ORB
  • images, matching with SIFT / Application – matching images with BRIEF, SIFT, and ORB
  • images, matching with ORB / Application – matching images with BRIEF, SIFT, and ORB
• scikit-image's astronaut dataset
  • using / Using scikit-image's astronaut dataset
• scikit-image filter.rank module
  • about / The scikit-image filter.rank module
  • morphological contrast enhancement / Morphological contrast enhancement
  • noise removal, with median filter / Noise removal with the median filter
  • local entropy, computing / Computing the local entropy
• scikit-image morphology module
  • about / The scikit-image morphology module
  • binary operations / Binary operations
• SciPy ndimage morphology module
  • about / The SciPy ndimage.morphology module
  • holes, filling in binary objects / Filling holes in binary objects
  • opening and closing, used to remove noise / Using opening and closing to remove noise
  • morphological (Beucher) gradient, computing / Computing the morphological Beucher gradient
  • morphological Laplace, computing / Computing the morphological Laplace
• seam carving
  • about / Seam carving
  • energy calculation / Seam carving
  • seam identification / Seam carving
  • seam removal / Seam carving
  • content-aware image resizing / Content-aware image resizing with seam carving
  • object removal / Object removal with seam carving
• seamless blending / Seamless cloning and Poisson image editing
• seamless cloning / Seamless cloning and Poisson image editing
• second-order partial derivatives / Some notes about the Laplacian
• seed points / Region growing with SimpleITK 
• sharpening
  • about / Sharpening and unsharp masking
  • with Laplacian / Sharpening with Laplacian
• SIFT descriptors
  • scale-space extrema detection / Algorithm to compute SIFT descriptors
  • keypoint localization / Algorithm to compute SIFT descriptors
  • orientation assignment / Algorithm to compute SIFT descriptors
  • keypoint descriptor computation / Algorithm to compute SIFT descriptors
  • algorithm, computing / Algorithm to compute SIFT descriptors
  • with opencv / With opencv and opencv-contrib
  • with opencv-contrib / With opencv and opencv-contrib
• Signal-to-Noise Ratio (SNR) / Quantizing with PIL
• signal to noise ratio (SNR) / How SNR changes with frequency cut-off, How SNR changes with frequency cutoff
• SimpleITK
  • region growing / Region growing with SimpleITK 
• single-channel / What is an image and how it is stored on a computer
• skeletonizing / Skeletonizing
• SLIC algorithm
  • about / Felzenszwalb, SLIC, QuickShift, and Compact Watershed algorithms , SLIC
  • RAG merging / RAG merging
• small object function
  • removing / Removing small objects
• SNR changes
  • with frequency cut-off / How SNR changes with frequency cut-off
• Sobel edge detector
  • with scikit-image / Sobel edge detector with scikit-image
• spectral clustering
  • for image segmentation / Spectral clustering for image segmentation
• spectrum of transform / Plotting the frequency spectrum
• squared Euclidean distance / Squared Euclidean distance
• stochastic gradient descent (SGD) / Classification with TF
• stride / Convolutional layer
• superpixels / Felzenszwalb, SLIC, QuickShift, and Compact Watershed algorithms 
• supervised machine learning
  • about / Supervised versus unsupervised learning
  • versus unsupervised machine learning / Supervised versus unsupervised learning
  • image classification / Supervised machine learning – image classification
  • object detection / Supervised machine learning – object detection
• SVM classifier / SVM classifier
• SVM model
  • classification / Classification with the SVM model

T

• TensorFlow (TF)
  • about / Image classification with TensorFlow or Keras
  • classification / Classification with TF
• texture synthesis / Texture synthesis
• texture transfer / Texture transfer
• thresholding
  • fixing / With a fixed threshold
  • about / Thresholding and Otsu's segmentation
• Total Variation Denoising / Total Variation Denoising
• Total Variation Inpainting / Image inpainting
• transfer learning
  • using / Transfer learning – what it is, and when to use it
  • with Keras / Transfer learning with Keras

U

• unsharp masking
  • about / Sharpening and unsharp masking, Unsharp masking
  • with SciPy ndimage module / With the SciPy ndimage module
• unsupervised machine learning
  • about / Supervised versus unsupervised learning, Unsupervised machine learning – clustering, PCA, and eigenfaces
  • versus supervised machine learning / Supervised versus unsupervised learning
  • K-means clustering, for image segmentation with color quantization / K-means clustering for image segmentation with color quantization
  • spectral clustering, for image segmentation / Spectral clustering for image segmentation
  • Principal Component Analysis (PCA) / PCA and eigenfaces 
  • eigenfaces / PCA and eigenfaces 
• unsupervised Wiener filter / Image deconvolution with the Wiener filter

V

• vanishing gradient problem / ResNet
• variational image processing
  • about / Variational image processing
  • Total Variation Denoising / Total Variation Denoising
  • flat-texture cartoonish images, creating with Total Variation Denoising / Creating flat-texture cartoonish images with total variation denoising
• Vector Quantization (VQ) / K-means clustering for image segmentation with color quantization
• VGG-16/19
  • about / VGG-16/19
  • used, for classifying cat/dog images in Keras / Classifying cat/dog images with VGG-16 in Keras
  • training phase / Training phase
  • testing phase / Testing (prediction) phase
• virtualenv
  • reference link / Installing pip
• Virtual Environment
  • reference link / Installing pip

W

• white top-hat / White and black top-hats

Y

• YOLO v2
  • about / Introducing YOLO v2 
  • images, classifying / Classifying and localizing images and detecting objects
  • objects, detecting / Classifying and localizing images and detecting objects
  • images, localizing / Classifying and localizing images and detecting objects
  • objects, proposing CNN used / Proposing and detecting objects using CNNs
  • objects, detecting CNN used / Proposing and detecting objects using CNNs
  • using / Using YOLO v2 
  • pre-trained YOLO model, used for object detection / Using a pre-trained YOLO model for object detection

Z

• zero-crossings / Laplacian
• zero-padded kernel / Deconvolution and inverse filtering with FFT