Viola-Jones method, HOG features, R-CNNs, YOLO and SSD (Single Shot) Object Detection Approaches with Python and OpenCV
What you'll learn
- Have a good understanding of the most powerful Computer Vision models
- Understand OpenCV
- Understand and implement Viola-Jones algorithm
- Understand and implement Histogram of Oriented Gradients (HOG) algorithm
- Understand and implement convolutional neural network (CNN) related computer vision approaches
- Understand and implement YOLO (You Only Look Once) algorithm
- Single Shot MultiBox Detection SDD algorithm
- Master face detection and object detection
- Basic Python programming skills
This course is about the fundamental concept of image processing, focusing on face detection and object detection. These topics are getting very hot nowadays because these learning algorithms can be used in several fields from software engineering to crime investigation. Self-driving cars (for example lane detection approaches) relies heavily on computer vision.
With the advent of deep learning and graphical processing units (GPUs) in the past decade it's become possible to run these algorithms even in real-time videos. So what are you going to learn in this course?
Section 1 - Image Processing Fundamentals:
- computer vision theory
- what are pixel intensity values
- convolution and kernels (filters)
- blur kernel
- sharpen kernel
- edge detection in computer vision (edge detection kernel)
- how to use computer vision approaches in lane detection
- Canny's algorithm
- how to use Hough transform to find lines based on pixel intensities
- Viola-Jones approach in computer vision
- what is sliding-windows approach
- detecting faces in images and in videos
- how to outperform Viola-Jones algorithm with better approaches
- how to detects gradients and edges in an image
- constructing histograms of oriented gradients
- using suppor vector machines (SVMs) as underlying machine learning algorithms
- what is the problem with sliding-windows approach
- region proposals and selective search algorithms
- region based convolutional neural networks (C-RNNs)
- fast C-RNNs
- faster C-RNNs
- what is the YOLO approach?
- constructing bounding boxes
- how to detect objects in an image with a single look?
- intersection of union (IOU) algorithm
- how to keep the most relevant bounding box with non-max suppression?
- what is the main idea behind SSD algorithm
- constructing anchor boxes
- VGG16 and MobileNet architectures
- implementing SSD with real-time videos
Thanks for joining the course, let's get started!
Who this course is for:
- Anyone interested in machine learning (artificial intelligence) and computer vision