At the end of 2018, students from LIDS presented their works at CIARP, an international conference which was held on Madrid, Spain. The Msc student Felipe Belem presented a work entitled: “Superpixel Segmentation by Object-based Iterative Spanning Forest”, which is an extension of the previously Iterative Spanning Forest (ISF) framework to include object information and present a superpixel segmentation method based on object saliency detection. It is show that the corresponding saliency maps can improve seed estimation and connectivity function, increasing the superpixel resolution inside a given object.
Jordão Bragantini, the another of LIDS students, was also invited to present his work at CIARP. It was entitled: “Graph-based Image Segmentation using Dynamic Trees”, and was a new framework proposed from extension of the IFT framework. The Dynamic IFT framework, can make object delineation more effective by exploiting color, texture, and shape information from those dynamic trees. In comparison with other graph-based approaches from the state-of-the-art, the experimental results on natural images show that DynIFT-based object delineation methods can be significantly more accurate.