Computer Vision is a branch of computer science concerned with the theory and practice of building systems that obtain information from images. NLeSC is actively involved in developing its expertise in this area. Examples of related tasks include (but are not limited to):
Segmentation algorithms have been used in the medical imaging domain – for automatic measurement of the hippocampus volume from brain MRI and for retina layers segmentation in OCT volumes. In a systems biology project, the C.elegans is extracted from high resolution and long videos capturing the behavior of the worm.
Algorithms have been developed for automatic salient regions extraction and matching, applicable for identification of animal or plant individuals or species identification as well scene recognition from multiple images taken under different viewing conditions. Interest point detection and matching have been used for generating point clouds from multiple images of an archeological object.
Currently, knowledge and experience is built on deep learning methods for image classification (using convolutional neural networks) in the context of Digital forensics. The software used is MATLABs Computer Vision Toolbox, ITK Toolbox, niftireg, OpenCV, etc. Currently deep learning packages are being explored.