Topologically-Guided Color Image Enhancement
This addresses image enhancement for applications like personal use, medical imaging, and object recognition, but it is incremental as it builds on existing topological methods.
The paper tackled the problem of image enhancement by proposing topology-aware transfer functions based on contour trees, which edit images using local topological properties rather than global ones, and evaluated the approach on grayscale and color images.
Enhancement is an important step in post-processing digital images for personal use, in medical imaging, and for object recognition. Most existing manual techniques rely on region selection, similarity, and/or thresholding for editing, never really considering the topological structure of the image. In this paper, we leverage the contour tree to extract a hierarchical representation of the topology of an image. We propose 4 topology-aware transfer functions for editing features of the image using local topological properties, instead of global image properties. Finally, we evaluate our approach with grayscale and color images.