Swarm Intelligence Methods for Unsupervised Images Classification: Applications and Comparative Study

Nowadays, Google estimates that more than 1000 billion the number of images on the internet where the classification of this type of data represents a big problem in the scientific community. Several techniques have been proposed belonging to the world of image-mining. The substance of our work is the application of swarm intelligence methods for the unsupervised image classification (UIC) problem following four steps: image digitalization by developing a new representation approach in order to transform each image into a set of term (set of pixels); image clustering using three methods: firstly a distances combination by social worker bees (DC-SWBs) based on the principle of filtering where each image must successfully pass three filters, secondly Artificial social spiders (ASS) method based on the silky structure and the principle of weaving and the third method called artificial immune system (AIS); For the authors' experiment they use the benchmark MuHavi with changing for each test the configuration (image representation, distance measures and threshold).