Aron Petau - gofai

Coding Examples

2021-03-01T00:00:00+00:00

Neural Networks and Computer Vision</h2>

A selection of coding projects</h2>
Although pure coding and debugging are often not a passion of mine, I recognize the importance of neural networks and other recent developments in Computer Vision. From several projects regarding AI and Machine Learning that I co-authored during my Bachelor Program, I picked this one since I think it is well documented and explains on a step-by-step basis what we do there.</p>

Image Super-Resolution using Convolutional Neural Networks (Recreation of a 2016 Paper)</h3>
Image Super-Resolution is a hugely important topic in Computer Vision. If it works sufficiently advanced, we could take all our screenshots and selfies and cat pictures from the 2006 facebook-era and even from before and scale them up to suit modern 4K needs.</p>
Just to give an example of what is possible in 2020, just 4 years after the paper here, have a look at this video from 1902:</p> </iframe>
The 2016 paper we had a look at is much more modest: it tries to upscale only a single Image, but historically, it was one of the first to achieve computing times sufficiently small to make such realtime-video-upscaling as visible in the Video (from 2020) or of the likes that Nvidia uses nowadays to upscale Videogames.</p>
Example of a Super-Resolution Image. The Neural network is artificially adding Pixels so that we can finally put our measly selfie on a billboard poster and not be appalled by our deformed-and-pixelated-through-technology face.</p>

</a>
A low-resolution sample</p> </li>
</a>
A high-resolution sample. This is also called 'ground truth'</p> </li>
</a>
The artificially enlarged image patch resulting from the algorithm</p> </li>
</a>
A graph showing an exemplary loss function applied during training</p> </li>
</a>
One qualitative measurement we used was pixel-wise cosine similarity. It is used to measure how similar the output and the ground truth images are</p> </li> </ul> </div>
The Python notebook for Image super-resolution in Colab</a></p>
MTCNN (Application and Comparison of a 2016 Paper)</h3>
Here, you can also have a look at another, much smaller project, where we rebuilt a rather classical Machine learning approach for face detection. Here, we use preexisting libraries to demonstrate the difference in efficacy of approaches, showing that Multi-task Cascaded Convolutional Networks (MTCNN) was one of the best-performing approaches in 2016. Since I invested much more love and work into the above project, I would prefer for you to check that one out, in case two projects are too much.</p>
Face detection using a classical AI Approach (Recreation of a 2016 Paper)</a></p>