The Image section hosts experts in image analysis and processing, computer vision, computer simulation, numerical optimization, information retrieval and machine learning. The work ranges from theoretical analyses, over algorithm development, to solving concrete problems for science, industry and society.
Labs and projects
Computer vision is concerned with the automated analysis of still images and videos. We focus on development of fundamental algorithms as well as applications of these to industrial and real-life problems.
The lab develops, analyses, and applies algorithms for machine learning and data mining. Our goal is to increase the autonomy and scalability of adaptive systems by using concepts from theoretical and applied computer science as well as statistics, optimization and applied mathematics. We love demonstrating the power of our methods by solving concrete problems in science and society.
The lab has its focus on modeling and numerical methods for nonlinear statistics, variational problems, and geometry on manifolds and metric spaces. Application areas include 3D tomographic reconstruction, airway trees, brain image and morphological analysis, and functional analysis of imaging data.
The team associated with the Numerical Optimization and Computer Simulation Lab is doing basic research in numerical methods, computational mechanics and computational physics with applications in robotics, computer games, visualization and biomechanincal modeling.
The Medical Image Analysis lab is concerned with the analysis of images for medical purposes. The major applications are neuroimaging, breast cancer screening and pulmonary images. The lab is focused on the quantification of pathological changes through medical imaging biomarkers.
Bioimaging is a term that collectively refers to tools used to creation and study of structural or functional images of living objects or systems.
The Information Retrieval Lab conducts research in the areas of information retrieval (e.g. search engines) and information extraction. We study and develop tools that provide effective and efficient access to big, hetereogeneous data.
Natural Language Processing (NLP) is a subfield of artificial intelligence, concerned with extracting linguistic information (e.g. grammatical, semantic, or pragmatic) from text. The NLP group at DIKU is interested in the biases that can influence NLP models and is actively working on improving the quality of NLP models for all languages, domains, and demographics.
The group is concerned with using Machine Learning techniques to solve problems in Biology. Currently, our main focus is on obtaining a better understanding of molecular structure, using a combination of techniques ranging from molecular simulation to deep learning.