A tutorials mini-series to learn Computer Vision from scratch

A list of Computer Vision tutorials. It starts from basic image processing using OpenCV (code needed is included), till real-world applications of Object Detection and Computer Vision, passing through enhancing and denoising images using autoencoders, and deploying interactive dashboards to detect objects in images. * Learn basic object detection and image processing functions using OpenCV

Read an image, extract the RGB values of a pixel, extract the Region of Interest (ROI), resize and rotate the image till building a pedestrians detector in traffic images

https://omdena.com/blog/opencv-pedestrian-detector/

* Learn advanced methods like adding noise to images then use autoencoders to produce clearer images and improve models results.

https://omdena.com/blog/denoising-images/

Learn the basics of CNNs and apply deep learning techniques using TensorFlow and Keras to classify MNIST dataset with code needed.

https://omdena.com/blog/applying-cnns/

To visualize your Computer Vision project, learn to build an interactive Streamlit application that takes the image and mask generated from a model as input and gives us the bounded box, mask outline, and heatmap. (With all code functions needed). https://omdena.com/blog/pathology-streamlit/

* Apply what you learned in a real-world project like using Computer Vision to help assess road crash risk at scale. By applying images labeling, object detection, CNNs, and various regression techniques to provide features for road safety estimation on roads globally.

https://omdena.com/blog/prevent-road-crashes/