There are several superpixel algorithms out there. One popular approach is called “Simple Linear Iterative Clustering” – short SLIC [1]. One implementation of SLIC is provided as part of the VLFeat library [2] which can be used from MatLab, but provides the C source code as well. This article shows how to use VLFeat’s implementation of SLIC from C++ using CMake.
In my sixth semester at RWTH Aachen University, I am currently attending a seminar offered by the Computer Vision Group headed by Prof. Leibe on “Current Topics in Computer Vision and Machine Learning”. In the course of this seminar, I wrote a seminar paper entitled “Understanding Convolutional Neural Networks”. Both the seminar paper as well as the slides of the corresponding talk can be found here.
Due to my bachelor thesis at RWTH Aachen University I am currently busy learning everything about superpixel segmentation — the oversegmentation of an image into groups of pixels using low-level features. In this article I want to give a short introduction by presenting my bachelor thesis proposal.