Visual object analysis is becoming more and more popular due to recent advances and availability of deep learning technologies. We present a use case we developed in the cloud to automate pill production quality control and save a pharmaceutical company millions of euros per year.
When a pill press breaks, it begins to produce defective pills that can take hours or sometimes days to recognize. With each pill press producing hundreds of pills per second, the monetary stakes of potentially losing days of product are high.
To address the issue, we prototyped a (deep) machine learning pipeline using transfer learning to detect defective pills. In the presentation, we address some of the challenges we faced (avoiding false positives, impact of image noise, dust and unwanted reflections etc.). We also show how we used statistical pre-processing techniques to reduce the amount of data needed and improve the quality of the prediction.
Target Audience: Decision makers in the manufacturing industry, IT-Experts interested in Deep Learning and Computer Vision
Prerequisites: Basic knowledge of Machine Learning and statistical models