Interactive Natural Image Segmentation / News: Recent posts

2009-aug-31: fixed important bugs, accelerating the pre-proc

2009-jun-15: Even more accurate version available. It explores color at pixel level, producing better image cut, enabling image composition / photomontage / background replacement.

News: 2009-jun-05: a new faster and more accurate version available for image segmentation.

An implementation of a new algorithm for Interactive Structural Segmentation described in

http://arxiv.org/abs/0805.1854

This paper proposes a novel algorithm for the problem of structural image segmentation through an interactive model-based approach. Interaction is expressed in the model creation, which is done according to user traces drawn over a given input image. Both model and input are then represented by means of attributed relational graphs derived on the fly. Appearance features are taken into account as object attributes and structural properties are expressed as relational attributes. To cope with possible topological differences between both graphs, a new structure called the deformation graph is introduced. The segmentation process corresponds to finding a labelling of the input graph that minimizes the deformations introduced in the model when it is updated with input information. This approach has shown to be faster than other segmentation methods, with competitive output quality. Therefore, the method solves the problem of multiple label segmentation in an efficient way.