Image Segmentation is an image analysis task in which we classify each pixel in the image into a class. This is similar to what us humans do all the time by default.

This lab will help you to understand how Convolutional Neural Networks works internally.

In deep learning, a convolutional neural network (CNN, or ConvNet) is a class of deep neural networks, most commonly applied to analyzing visual imagery. They are also known as shift invariant or space invariant artificial neural networks (SIANN), based on their shared-weights architecture and translation invariance characteristics. They have applications in image and video recognition, recommender systems, image classification, medical image analysis, and natural language processing.

But let's focus on Image Segmentation (IS). IS allows us to recognize different objects, textures, people, animals... And separate them from the image's background. Thus we can apply diferrent filters to the backgroud o foreground to stick out or depress that object in order to reduce the image's noise.

Open the main.ipynb. There are a bunch of questions to be solved. Read each instruction carefully and provide your answer beneath it.

• main.ipynb with your responses
• a background blurred image

Upon completion, add your deliverables to git. Then commit git and push your branch to the remote.

https://leonardoaraujosantos.gitbooks.io/artificial-inteligence/content/image_segmentation.html

https://towardsdatascience.com/image-segmentation-using-pythons-scikit-image-module-533a61ecc980

https://www.analyticsvidhya.com/blog/2019/04/introduction-image-segmentation-techniques-python/

https://www.analyticsvidhya.com/blog/2017/06/architecture-of-convolutional-neural-networks-simplified-demystified/?utm_source=blog&utm_medium=image-segmentation-article

https://www.learnopencv.com/pytorch-for-beginners-semantic-segmentation-using-torchvision/

https://www.kaggle.com/sanikamal/image-segmentation-using-color-spaces