nextml

We helped our customer to improve their solution for reading text in images specialized to their environment and went from 4% error rate to a much better 0.2%.

Similar applications

You can use the exact same solution to do super-resolution or in-painting for another domain, such as fashion. Just replace the dataset with the images you want.

If you have something similar in mind, schedule a meeting, and let’s talk!

other projects

Super-resolution and removing objects in satellite images

The goal of this project was to make accesible satellite data easier to work with by removing unecessary objects and by increasing the resolution.

Extensive video-search using CLIP and DiskANN

Using new advancements in connecting text and images, we helped a large media production company implement effective video search without the need for meta-data.

Detecting damages on railroad infrastructure

Together with Infranord and Trafikverket, we’ve developed machine learning algorithms for detecting damages on railroad infrastructure.

Unsupervised segmentation of satellite images

Our assignment was to develop an algorithm that segments satellite images into distinct areas based on vegetation without any labeled training data.

Text recognition in factories for a large manufacturer