One of the major challenges in deep learning is retrieving sufficiently large labeled training datasets, which can become expensive and time consuming to collect. A unique approach to training segmentation is to use Deep Neural Network (DNN) models with a minimal amount of initial labeled training samples. The procedure involves creating synthetic data and using image registration to calculate affine transformations to apply to the synthetic data. The method takes a small dataset and generates a highquality augmented reality synthetic dataset with strong variance while maintaining consistency with real cases. Results illustrate segmentation improvements in various target features and increased average target confidence.
Kevin Payumo, Alexander Huyen, Landan Seguin, Thomas T. Lu, Edward Chow, and Gil Torres, "Augmented reality data generation for training deep learning neural network," Proc. SPIE 10649, Pattern Recognition and Tracking XXIX, 106490U (Presented at SPIE Defense + Security: April 19, 2018; Published: 30 April 2018); https://doi.org/10.1117/12.2305202.
Conference Presentations are recordings of oral presentations given at SPIE conferences and published as part of the proceedings. They include the speaker's narration with video of the slides and animations. Most include full-text papers. Interactive, searchable transcripts and closed captioning are now available for 2018 presentations, with transcripts for prior recordings added daily.
Search our growing collection of more than 16,000 conference presentations, including many plenaries and keynotes.