Detection of surface defects on pharmaceutical solid oral dosage forms with convolutional neural networks

Deep-learning-based approaches have proven to outperform other approaches in various computer vision tasks, making application-focused machine learning a promising area of research in automated visual inspection. In this work, we apply deep learning to the challenging real-world problem domain of automated visual inspection of pharmaceutical products. We focus on investigating whether compact network architectures, adhering to performance, resource, and accuracy requirements, are suitable for usage in the pharmaceutical visual inspection domain. We propose a compact and efficient convolutional neural network architecture design for segmentation and scoring of surface defects, which we evaluate on challenging real-world datasets from the pharmaceutical product-inspection domain. In comparison with other related segmentation approaches, we achieve state-of-the-art performance in terms of defect detection as well as real-time computational efficiency. Compared to the nearest best-performing architecture we achieve state-of-the-art performance with merely 3% of the parameter count, an approximately 8-fold increase in inference speed, and increased surface defect detection performance.