Cargando…
Learn computer vision using OpenCV : with deep learning CNNs and RNNs /
Build practical applications of computer vision using the OpenCV library with Python. This book discusses different facets of computer vision such as image and object detection, tracking and motion analysis and their applications with examples. The author starts with an introduction to computer visi...
| Clasificación: | Libro Electrónico |
|---|---|
| Autor principal: | |
| Formato: | Electrónico eBook |
| Idioma: | Inglés |
| Publicado: |
[New York, NY] :
Apress,
[2019]
|
| Temas: | |
| Acceso en línea: | Texto completo (Requiere registro previo con correo institucional) |
Tabla de Contenidos:
- Intro; Table of Contents; About the Author; About the Technical Reviewer; Acknowledgments; Foreword; Introduction; Chapter 1: Artificial Intelligence and Computer Vision; Introduction to Artificial Intelligence; Natural Language Processing; Robotics; Machine Learning; Expert Systems; Speech and Voice Recognition; Intelligent Process Automation; Introduction to Computer Vision; Scope; Challenges of Computer Vision; Real-World Applications of Computer Vision; Automotive Industry; Healthcare and Biomedical Industry; Retail Industry; Images and Their Features; Color Spaces
- Core Building Blocks (Input
- Process
- Output)Optical Character Recognition and Intelligent Character Recognition; Optical Mark Recognition; Conclusion; Chapter 2: OpenCV with Python; About OpenCV; Setting Up OpenCV with Python; Windows Installation; macOS Installation; Using Modules; Working with Images and Videos; Using NumPy; Reading and Loading Images with OpenCV and NumPy; Working with a Histogram Representation; Videos; Loading Videos from a Webcam; Loading Videos from a File; Reading the Video and Writing into a File; Conclusion; Chapter 3: Deep Learning for Computer Vision
- Deep Learning: An OverviewDeep Learning Applications in Computer Vision; Classification; Detection and Localization; (Semantic) Segmentation; Similarity Learning; Image Captioning; Generative Models; Video Analysis; Neural Networks at Their Core; Artificial Neural Networks; Artificial Neurons or Perceptrons; Training Neural Networks; Backpropagation; Gradient Descent and Stochastic Gradient Descent; Convolutional Neural Networks; Convolution Layer; Pooling Layer; Fully Connected Layer; Recurrent Neural Networks; Backpropagation Through Time; Conclusion
- Chapter 4: Image Manipulation and SegmentationImage Manipulations; Accessing and Manipulating Pixels; Drawing Geometric Shapes or Writing Text on a Color Image; Filtering Images; Transforming Images; Translation; Rotation; Image Scaling; Edge Detection; Image Segmentation; Line Detection; Circle Detection; Conclusion; Chapter 5: Object Detection and Recognition; Basics of Object Detection; Object Detection vs. Object Recognition; Template Matching; Challenges with Template Matching; Understanding Image "Features"; Interesting and Uninteresting Points; Types of Image Features; Feature Matching
- Image Corners As FeaturesHarris Corner Algorithm; Feature Tracking and Matching Flow; Scale Variant Feature Transform; Speeded-Up Robust Features; Features from Accelerated Segment Test; Binary Robust Independent Elementary Features; Oriented FAST and Rotated BRIEF; Conclusion; Chapter 6: Motion Analysis and Object Tracking; Introduction to Object Tracking; Challenges of Object Tracking; Object Detection Techniques for Tracking; Frame Differentiation; Background Subtraction; Optical Flow; Lucas-Kanade Differential Algorithm; Dense Optical Flow Algorithm; Object Classification