Index
A
- affine transformations
- augmented reality
- about / What is the premise of augmented reality?
- geometric transformations / Geometric transformations for augmented reality
- augmented reality system
B
- background subtraction
- about / Background subtraction
- Bag of Words / What happened inside the code?
- Binary Robust Independent Elementary Features (BRIEF)
- blurring
- about / Blurring
- boomerang shape
- identifying / Contour analysis and shape matching
C
- Caltech256
- camera-to-image transformation / Geometric transformations for augmented reality
- CAMShift algorithm
- Canny Edge Detector
- URL / Edge detection
- cartoonize_image function / Deconstructing the code
- colored objects
- tracking, colorspaces used / Colorspace based tracking
- color images
- handling / How do we handle color images?
- color spaces
- RGB / Image color spaces
- YUV / Image color spaces
- HSV / Image color spaces
- converting between / Converting between color spaces, What just happened?
- colorspaces
- used, for tracking colored objects / Colorspace based tracking
- about / Colorspace based tracking
- contour
- approximating / Approximating a contour
- contour analysis
- convex shapes
- convolution
- about / 2D convolution
- coordinates
- mapping, from 3D to 2D / Mapping coordinates from 3D to 2D
- corner detection
- reference link / Detecting the corners
- corner point
- about / Detecting the corners
- corners
- detecting / Detecting the corners
- cross-ratio
- reference link / Projective transformations
- cv2.rectangle() function / What's happening underneath?
D
- 2D Convolution / 2D convolution
- 3D map
- building / Building the 3D map
- 3D objects
- overlaying, on top of real world / How to augment our reality?
- overlaying, on video / How to overlay 3D objects on a video?, Let's look at the code
- Deep Learning
- dense feature detector
- dilation
- about / Erosion and dilation
- using / Afterthought
E
- ears
- detecting / Detecting ears
- edge detection
- process / Edge detection
- about / Edge detection
- embossing filter
- about / Embossing
- epipolar geometry
- about / What is epipolar geometry?
- epipolar lines
- about / What is epipolar geometry?
- versus SIFT / Why are the lines different as compared to SIFT?
- epipole
- about / What is epipolar geometry?
- erosion
- about / Erosion and dilation
- using / Afterthought
- eyes
- detecting / Detecting eyes, Afterthought
- sunglasses, positioning / Fun with eyes, Positioning the sunglasses
F
- faces
- detecting / Detecting and tracking faces, Understanding it better
- tracking / Detecting and tracking faces, Understanding it better
- funny masks, overlaying on / Fun with faces, Under the hood
- feature based tracking
- about / Feature based tracking
- Features from Accelerated Segment Test (FAST)
- feature tracker
- building / Feature based tracking
- Flann
- frame differencing
- using / Frame differencing
- fundamental matrix
- about / What is epipolar geometry?
- funny masks
- overlaying, on top of faces / Fun with faces, Under the hood
G
- Gaussian Mixture Markov Random Field (GMMRF)
- about / How does it work?
- URL / How does it work?
- geometric transformations, for augmented reality
- about / Geometric transformations for augmented reality
- object-to-scene / Geometric transformations for augmented reality
- scene-to-camera / Geometric transformations for augmented reality
- camera-to-image / Geometric transformations for augmented reality
- GrabCut
- about / What is image segmentation?
- reference link / What is image segmentation?
- graph-cuts
- about / What is image segmentation?
H
- Haar cascades
- used, for detecting things / Using Haar cascades to detect things
- Hamming distance
- Harris Corner Detector
- about / Detecting the corners
- Histogram Equalization / Enhancing the contrast in an image
- Homebrew
- about / Mac OS X
- homography
- about / Projective transformations
- HSV color space / Image color spaces
- HSVcolorspace
- about / Colorspace based tracking
I
- image
- contrast, enhancing / Enhancing the contrast in an image
- color images, handling / How do we handle color images?
- cartoonizing / Cartoonizing an image
- code, deconstructing / Deconstructing the code
- expanding / Can we expand an image?
- image color spaces
- about / Image color spaces
- image content analysis
- about / Why do we care about keypoints?
- image filter / 2D convolution
- image rotation
- about / Image rotation, What just happened?
- images
- reading / Reading, displaying, and saving images
- displaying / Reading, displaying, and saving images
- saving / Reading, displaying, and saving images, Loading and saving an image
- loading / Loading and saving an image
- stitching / Stitching the images
- stretched image, reason / Why does it look stretched?
- image scaling
- about / Image scaling, What just happened?
- image segmentation
- about / What is image segmentation?
- working / How does it work?
- image translation
- about / Image translation, What just happened?
- image warping
- about / Image warping
- incidence
- reference link / Projective transformations
- installing
- OpenCV-Python / Installing OpenCV-Python
- OpenCV-Python, on Windows / Windows
- OpenCV-Python, on Mac OS X / Mac OS X
- OpenCV-Python, on Linux (for Ubuntu) / Linux (for Ubuntu)
- integral images
- about / What are integral images?
- interactive object tracker
- building / Building an interactive object tracker
K
- K-Means clustering
- about / How to censor a shape?
- reference link / How to censor a shape?
- kernel / 2D convolution
- kernel size
- versus blurriness / The size of the kernel versus the blurriness
- kernel trick
- keyboard inputs
- about / Keyboard inputs
- application, interacting with / Interacting with the application
- keypoint descriptors
- matching / Matching keypoint descriptors
- keypoints
- need for / Why do we care about keypoints?
- about / What are keypoints?
- matching / How did we match the keypoints?
L
- Linux (for Ubuntu)
- OpenCV-Python, installing on / Linux (for Ubuntu)
- live video stream
- interacting with / Interacting with a live video stream
- working with / How did we do it?
- low pass filter / Blurring
- Lucas-Kanade method
- about / Feature based tracking
- reference link / Feature based tracking
M
- Mac OS X
- OpenCV-Python, installing on / Mac OS X
- matcher object
- about / Understanding the matcher object
- item.distance attribute / Understanding the matcher object
- item.trainIdx attribute / Understanding the matcher object
- item.queryIdx attribute / Understanding the matcher object
- item.imgIdx attribute / Understanding the matcher object
- matching keypoints
- drawing / Drawing the matching keypoints
- Meanshift algorithm
- MeshLab
- about / Building the 3D map
- URL / Building the 3D map
- moments
- reference link / Contour analysis and shape matching
- motion blur
- about / Motion blur
- using / Under the hood
- mouse inputs
- about / Mouse inputs
- using / What's happening underneath?
- detect_quadrant function / What's happening underneath?
- moustache
- overlaying / It's time for a moustache
- mouth
- detecting / Detecting a mouth
- multiple images
- capturing, on same plane / What if the images are at an angle to each other?
N
- nose
- detecting / Detecting a nose
- NumPy
- about / Windows
- URL, for installation / Windows
- URL / What just happened?
O
- object
- removing / Can we remove an object completely?, How did we do it?
- recognizing, in unknown image / What happened inside the code?
- object-to-scene transformation / Geometric transformations for augmented reality
- object detection
- versus object recognition / Object detection versus object recognition
- object recognition
- versus object detection / Object detection versus object recognition
- OpenCV
- URL, for downloading / Windows
- URL, for downloads page / Linux (for Ubuntu)
- reference link, for modules / Mapping coordinates from 3D to 2D
- OpenCV-Python
- installing / Installing OpenCV-Python
- installing, on Windows / Windows
- installing, on Mac OS X / Mac OS X
- installing, on Linux (for Ubuntu) / Linux (for Ubuntu)
- optical flow
- about / Feature based tracking
- optical flow based tracking
- performing / Feature based tracking
- ord() function / Interacting with the application
- Oriented FAST and Rotated BRIEF (ORB)
P
- panoramic image
- creating / Creating the panoramic image
- overlapping regions, finding / Finding the overlapping regions
- pip
- about / Mac OS X
- pizza
- identifying, with slice taken out / Identifying the pizza with the slice taken out
- planar objects
- pose estimation
- about / What is pose estimation?
- projective transformations
- pupils
- detecting / Detecting pupils
- code, deconstructing for detection / Deconstructing the code
- pyramid height
- modifying, dynamically / Let's add some movements
- Python 2.7.x
- URL, for installation / Windows
R
- RGB color space / Image color spaces
S
- Scale Invariant Feature Transform (SIFT)
- using / Scale Invariant Feature Transform (SIFT)
- reference link / Scale Invariant Feature Transform (SIFT)
- scene-to-camera transformation / Geometric transformations for augmented reality
- seam carving
- about / Why do we care about seam carving?
- working / How does it work?
- reference link / How does it work?
- seams
- computing / How do we compute the seams?
- shape
- censoring / How to censor a shape?
- shape matching
- sharpening filter
- about / Sharpening
- using / Understanding the pattern
- Shi-Tomasi corner detector
- about / Good Features To Track
- SIFT
- versus epipolar lines / Why are the lines different as compared to SIFT?
- Sobel Filter
- about / How do we define "interesting"?
- solidity factor
- about / How to censor a shape?
- Speeded Up Robust Features (SURF)
- using / Speeded Up Robust Features (SURF)
- references / Speeded Up Robust Features (SURF)
- stereo correspondence
- about / What is stereo correspondence?
- supervised learning
- Support Vector Machines (SVM)
- about / What are Support Vector Machines?
- classifier, building / How do we actually implement this?
- SURF feature extractor
- about / What is epipolar geometry?
- SVM model
- building / How did we build the trainer?
U
- unknown image
- object, recognizing in / What happened inside the code?
- unsupervised learning
V
- vector quantization / What is a visual dictionary?
- video
- 3D objects, overlaying on / How to overlay 3D objects on a video?, Let's look at the code
- VideoCapture function / Under the hood
- video surveillance system
- building / Background subtraction
- vignette filter
- creating / Creating a vignette filter
- using / What's happening underneath?
- effect, achieving / How do we move the focus around?
- Viola-Jones method
- about / Using Haar cascades to detect things
- reference link / Using Haar cascades to detect things
- visual dictionary
- about / What is a visual dictionary?
W
- waitKey() function / Interacting with the application
- watershed algorithm
- about / Watershed algorithm
- reference link / Watershed algorithm
- webcam
- accessing / Accessing the webcam, Under the hood
- VideoCapture function, using / Under the hood
- Windows
- OpenCV-Python, installing on / Windows
Y
- YUV color space / Image color spaces