In the previous article about contrast stretching, we explored percentile contrast stretching and how to apply this to obtain better performance in object detection models. Percentile contrast stretching is also called (histogram) normalization, as we normalize the range of the pixel intensities.
An important part of training neural networks is preprocessing of the input. A lot of performance gain can be obtained by carefully examining, cleaning and transforming the input data.
As stated in our previous post, we are going to make a model to extract information from satellite images to help estimating the number of refugees in refugee camps in Nigeria. In this post we will dive some deeper into this goal. We will answer the questions “How do we want to make this model work?” and “How is this going to help in estimating the number of refugees?”
We proudly announce the participation of Notilyze in the SAS EMEA Hackathon. The Hackathon will take place in February and the goal is to find a way to add sustainable value in real life business. We will take this challenge in cooperation with ELVA Community Engagement and the International Organization for Migration.
In collaboration with the ComplianceAgency, Notilyze is working on a new information security system, so that we can assure you that your data will be and remain safe with us.
During the Big Data Expo, Colin Nugteren was interviewed by Werner Schoots from BI Platform. During this interview, the developments and activities inside Notilyze were discussed, but they also talked about the new opportunities and possibilities that still exist in the current market.
