OpenCV_Projects

This repository includes any projects that I have completed in research, projects, or online classes: (Rajeev Ratan) and Satya Mallick (CEO) AI OpenCV Bootcamp. My main focus is to study fields that cross over Machine Learning (Convolutionary Neural Network, Support Vector Machines, and Clustering of K-means), Computer Vision and Data Science.

Contents:

1. Basics of Computer Vision and OpenCV
2. Image Manipulation and Processing
3. Image Segmentation and Contours
4. Object Detection Part 1: Intro
5. Object Detection Part 2: Build a Face, people and Car Detectors
6. Augmented Reality (AR): Facial Landmark Identification
7. Simple Machine Learning using OpenCV
8. Object Tracking and Motion Analysis
9. Computational Photography
10. Self Driving Cars
11. Deep Learning

Sections:

Basics of Computer Vision and OpenCV

(Return back to Contents)

Image Processing. Learn some of the basics of image processing such as blurring an image, understanding image morphology, geometric transforms, and image histograms.

OpenCV Intro		Learn how to display a simple image plt.imshow(cv2.cvtColor(input, cv2.COLOR_BGR2RGB))
Grayscaling		Grayscaling is a very popular technique in computer vision to find the gradient on edge points of an image.
Colors HSV-Hue		Now we know how to convert BGR image to HSV, we can use this to extract a colored object. In HSV, it is more easier to represent a color than in BGR color-space. In our application, we will try to extract a blue colored object.
Colors Gray-RGB		In OpenCV we can convert an RGB image into Grayscale by two ways: 1. By using cvtColor function. 2. By using imread function, where the first parameter specifies the image name while the second parameter specifies the format in which we need to add the image.
Color Red-Green-Blue		Computers can only understand three colors: red, green, and blue. This topic helps us tweek the color intensity in RGB.
Histogram		Histogram helps us understaqnd the distribution behind the colors of an image. This is important to know when you plan on compiling a machine learning algorithm with a balanced dataset

Image Manipulation and Processing

(Return back to Contents)

In this section we are going to see how we are going to manipulate the image using OpenCV. Here we will learn to apply the following function on an image using OpenCV: (1) Image Transformations – Affine and Non-Affine Transformation (2) Image Translations – Moving image up, down, left and right (3) Rotation of image – Spinning the image (4) Scaling, Resizing, and Interpolation (5) Image Pyramids – Another way of resizing (6) Cropping – Cutting out the image region you want (7) Arithmetic operations for Brightening and Darkening of images

Transformation		In this chapter we learn how to transform images for rotation, scaling, bitwise pixel manipulations and edge detection. Before sending a picture or frame into a computer vision model, we need to adjust the features (histogram) in order to change quality.
Img Translation		Img Translation will help you crop your picture to adjust the features within your input. For example if you needed to train an AI to detect a specific object, you would want to crop your main label and avoid pixels irrelevant to what your detecting.
Rotations		Sometimes objects in an a image that need to be trained are not properly positioned correctly to help the AI understand the features we want to aggregate. Usuaing rotations we can help position the object correctly to help train our algorithm.
Scaling		Sometimes zooming into a picture looses pixel quality. With scaling in opencv, we can generate new pixels to prevent blury content with zooming in.
Image Pyramids (Resize)		Learn how to resize images to for visiual designers
Region of intrest (Crop)		In self driving cars we need to focus on street lanes in order to teach a car to drive by itself. With region of interest, we can crop out a section of an image and focus on the pixels representing a street (Mode info under section (#Self-Driving-Cars))