Open Archive Toulouse Archive OuverteOATAO is an open access repository that collects the work of Toulouse researchers and makes it freely available over the web where possible Abstract. This paper addresses the problem of interactive multiclass segmentation of images. We propose a fast and efficient new interactive segmentation method called superpixel α fusion (SαF). From a few strokes drawn by a user over an image, this method extracts relevant semantic objects. To get a fast calculation and an accurate segmentation, SαF uses superpixel oversegmentation and support vector machine classification. We compare SαF with competing algorithms by evaluating its performances on reference benchmarks. We also suggest four new datasets to evaluate the scalability of interactive segmentation methods, using images from some thousand to several million pixels. We conclude with two applications of SαF.

Using superpixels instead of pixels has become a popular pre-processing step in computer vision. Currently, about fifteen oversegmentation methods have been proposed. The last evaluation, realized by Stutz et al. in 2015, concludes that the five more competitive algorithms achieve similar results. By introducing HSID, a new dataset, we point out unexpected difficulties encountered by state-of-the-art oversegmentation methods.

Using superpixels instead of pixels has become a popular pre-processing step in computer vision. However, there are few adaptive methods able to automatically find the best comprise between boundary adherence and superpixel number. Moreover, no algorithm producing color and texture homogeneous superpixels keeps competitive execution time. In this article we suggest a new graph-based region merging method, called Adaptive Superpixel Algorithm with Rich Information (ASARI) to solve these two difficulties. We will show that ASARI achieves results similar to the state-of-the-art methods on the existing benchmarks and outperforms these methods when dealing with big images.