Automatic Image Segmentation by Tree Pruning
Journal of Mathematical Imaging and Vision
Object delineation by κ-connected components
EURASIP Journal on Advances in Signal Processing
Links Between Image Segmentation Based on Optimum-Path Forest and Minimum Cut in Graph
Journal of Mathematical Imaging and Vision
Synergistic arc-weight estimation for interactive image segmentation using graphs
Computer Vision and Image Understanding
Fast interactive segmentation of natural images using the image foresting transform
DSP'09 Proceedings of the 16th international conference on Digital Signal Processing
Textural image segmentation using discrete cosine transform
CIT'09 Proceedings of the 3rd International Conference on Communications and information technology
| Hi-index | 0.00 |
The Image Foresting Transform (IFT) has been proposed for the design of image operators based on connectivity. The IFT reduces image processing problems into a minimum-cost path forest problem in a graph derived from the image. It has been successfully used for image filtering, segmentation, and analysis. In this work, we propose a novel image operator which solves segmentation by pruning trees of the forest. First, an IFT is applied to create an optimum-path forest whose roots are pixels selected inside a desired object. In this forest, the background consists of a few subtrees rooted at pixels on the object's boundary. These boundary pixels are identified and their subtrees are eliminated, such that the remaining forest definesthe object. The tree pruning is an effective alternative to situations where image segmentation methods based on competing seeds fail. We present an interactive implementation of the tree-pruning technique, show several examples and discuss some experiments toward fully automatic segmentation.