At Landing AI, I have gone through several projects where we developed an end-to-end machine-learning system from “scratch'“. That means before we started on the project, there was no existing data collection procedure, so we had to start from zero and set up cameras.

The first step in collecting training data for machine vision is to design an image acquisition system. A well-designed image acquisition system will boost your model’s accuracy and sensitivity. On the other hand, a poorly designed imaging solution will definitely have negative impacts. We’ve encountered scenarios when in the middle of our model iteration, we would find our model’s performance negatively impacted by the input imaging quality. This meant going back and readjusting cameras and/or the environment. Every time we make such a change, the data distribution changes. This in turn forces us to collect new data and retrain the model. Such process is costly.

We learned from our past experience and developed knowledge and processes of designing good image acquisition systems. Some of the knowledge was shared earlier in this Tech Talk on Photography. Recently, I wrote a blog on Designing Image Acquisition for Machine Vision and published at Landing AI’s website. You can find it here.