A repository where I practice the fundamentals of computer vision. These notes are based off my work on the Computer Vision Nanodegree from Udacity. Note that this is not an affiliate link and I don't receive any compensation from Udacity whatsoever.

The code and comments are purely to help myself and those who are interested in studying and learning about computer vision.

The following libraries are required

• numpy
• open cv
• matplotlib

Note that image captioning and object detection is performed on the MS-coco dataset provided by microsoft. To get the example working, we need to first download the dataset. There are many working examples online (for example, here)