ASARI: a new adaptive oversegmentation method

Abstract

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.