This dataset aims at the comparison of the automatic nonlinear image registration of 2D microscopy images of histopathology tissue samples stained with different dyes.
In digital pathology, it is often useful to align spatially close but differently stained tissue sections in order to obtain the combined information. The images are large, in general, their appearance and their local structure are different, and they are related through a nonlinear transformation. The introduces dataset together with BIRL framework focus on comparing the accuracy and approximative speed of automatic non-linear registration methods for this task. Registration accuracy will be evaluated using manually annotated landmarks (included in the dataset).
The Ground truth is denoted using landmarks - key points that are marked consistently for each set of images with different stains.