Machine learning of hierarchical clustering to segment 2D and 3D images
This work addresses segmentation challenges in fields like neuroscience and computer vision, though it appears incremental as it builds on existing hierarchical clustering methods.
The paper tackled the problem of image segmentation by proposing an active learning approach for hierarchical agglomerative segmentation from superpixels, demonstrating an improvement over competing algorithms in 3D electron microscopy and natural images using variation of information as a metric.
We aim to improve segmentation through the use of machine learning tools during region agglomeration. We propose an active learning approach for performing hierarchical agglomerative segmentation from superpixels. Our method combines multiple features at all scales of the agglomerative process, works for data with an arbitrary number of dimensions, and scales to very large datasets. We advocate the use of variation of information to measure segmentation accuracy, particularly in 3D electron microscopy (EM) images of neural tissue, and using this metric demonstrate an improvement over competing algorithms in EM and natural images.