Practical computer vision extract insightful information from images using TensorFlow, Keras, and OpenCV
A practical guide designed to get you from basics to current state of art in computer vision systems. About This Book Master the different tasks associated with Computer Vision and develop your own Computer Vision applications with ease Leverage the power of Python, Tensorflow, Keras, and OpenCV to...
| Otros Autores: | |
|---|---|
| Formato: | Libro electrónico |
| Idioma: | Inglés |
| Publicado: |
Birmingham, England ; Mumbai, [India] :
Packt
2018.
|
| Edición: | 1st edition |
| Materias: | |
| Ver en Biblioteca Universitat Ramon Llull: | https://discovery.url.edu/permalink/34CSUC_URL/1im36ta/alma991009631651106719 |
Tabla de Contenidos:
- Cover
- Title Page
- Copyright and Credits
- Dedication
- Packt Upsell
- Contributors
- Table of Contents
- Preface
- Chapter 1: A Fast Introduction to Computer Vision
- What constitutes computer vision?
- Computer vision is everywhere
- Getting started
- Reading an image
- Image color conversions
- Computer vision research conferences
- Summary
- Chapter 2: Libraries, Development Platform, and Datasets
- Libraries and installation
- Installing Anaconda
- NumPy
- SciPy
- Jupyter notebook
- Installing OpenCV
- OpenCV Anaconda installation
- OpenCV build from source
- Opencv FAQs
- TensorFlow for deep learning
- Keras for deep learning
- Datasets
- ImageNet
- MNIST
- CIFAR-10
- Pascal VOC
- MSCOCO
- TUM RGB-D dataset
- Summary
- References
- Chapter 3: Image Filtering and Transformations in OpenCV
- Datasets and libraries required
- Image manipulation
- Introduction to filters
- Linear filters
- 2D linear filters
- Box filters
- Properties of linear filters
- Non-linear filters
- Smoothing a photo
- Histogram equalization
- Median filter
- Image gradients
- Transformation of an image
- Translation
- Rotation
- Affine transform
- Image pyramids
- Summary
- Chapter 4: What is a Feature?
- Features use cases
- Datasets and libraries
- Why are features important?
- Harris Corner Detection
- FAST features
- ORB features
- FAST feature limitations
- BRIEF Descriptors and their limitations
- ORB features using OpenCV
- The black box feature
- Application - find your object in an image
- Applications - is it similar?
- Summary
- References
- Chapter 5: Convolutional Neural Networks
- Datasets and libraries used
- Introduction to neural networks
- A simple neural network
- Revisiting the convolution operation
- Convolutional Neural Networks
- The convolution layer.
- The activation layer
- The pooling layer
- The fully connected layer
- Batch Normalization
- Dropout
- CNN in practice
- Fashion-MNIST classifier training code
- Analysis of CNNs
- Popular CNN architectures
- VGGNet
- Inception models
- ResNet model
- Transfer learning
- Summary
- Chapter 6: Feature-Based Object Detection
- Introduction to object detection
- Challenges in object detection
- Dataset and libraries used
- Methods for object detection
- Deep learning-based object detection
- Two-stage detectors
- Demo - Faster R-CNN with ResNet-101
- One-stage detectors
- Demo
- Summary
- References
- Chapter 7: Segmentation and Tracking
- Datasets and libraries
- Segmentation
- Challenges in segmentation
- CNNs for segmentation
- Implementation of FCN
- Tracking
- Challenges in tracking
- Methods for object tracking
- MOSSE tracker
- Deep SORT
- Summary
- References
- Chapter 8: 3D Computer Vision
- Dataset and libraries
- Applications
- Image formation
- Aligning images
- Visual odometry
- Visual SLAM
- Summary
- References
- Chapter 9: Mathematics for Computer Vision
- Datasets and libraries
- Linear algebra
- Vectors
- Addition
- Subtraction
- Vector multiplication
- Vector norm
- Orthogonality
- Matrices
- Operations on matrices
- Addition
- Subtraction
- Matrix multiplication
- Matrix properties
- Transpose
- Identity matrix
- Diagonal matrix
- Symmetric matrix
- Trace of a matrix
- Determinant
- Norm of a matrix
- Getting the inverse of a matrix
- Orthogonality
- Computing eigen values and eigen vectors
- Hessian matrix
- Singular Value Decomposition
- Introduction to probability theory
- What are random variables?
- Expectation
- Variance
- Probability distributions
- Bernoulli distribution
- Binomial distribution
- Poisson distribution
- Uniform distribution.
- Gaussian distribution
- Joint distribution
- Marginal distribution
- Conditional distribution
- Bayes theorem
- Summary
- Chapter 10: Machine Learning for Computer Vision
- What is machine learning?
- Kinds of machine learning techniques
- Supervised learning
- Classification
- Regression
- Unsupervised learning
- Dimensionality's curse
- A rolling-ball view of learning
- Useful tools
- Preprocessing
- Normalization
- Noise
- Postprocessing
- Evaluation
- Precision
- Recall
- F-measure
- Summary
- Other Books You May Enjoy
- Index.
