A lot of research has been done on author classification using various methodologies. One of them is using artificial neural networks. It is common that the number of descriptors used for author classification exceeds two. In this paper we propose a means of using artificial neural network to classify the authors of texts using only two descriptors: the number of words in a paragraph and a number of characters per word in a paragraph. The approach taken uses committee machines based on ensemble averaging. The basic idea is to solve the complex computational task by dividing it into a number of computationally simple tasks and then combining the solution of these tasks. The high performance achieved is because the committee is much better than the single best constituent in the isolation. Our results show that with the above approach we succeeded to correctly classify the works of Leo Tolstoy and George Orwell.

We present a rectangle-based segmentation algorithm that sets up a graph and performs a graph cut to separate an object from the background. However, graph-based algorithms distribute the graph's nodes uniformly and equidistantly on the image. Then, a smoothness term is added to force the cut to prefer a particular shape. This strategy does not allow the cut to prefer a certain structure, especially when areas of the object are indistinguishable from the background. We solve this problem by referring to a rectangle shape of the object when sampling the graph nodes, i.e., the nodes are distributed non-uniformly and non-equidistantly on the image. This strategy can be useful, when areas of the object are indistinguishable from the background. For evaluation, we focus on vertebrae images from Magnetic Resonance Imaging (MRI) datasets to support the time consuming manual slice-by-slice segmentation performed by physicians. The ground truth of the vertebrae boundaries were manually extracted by two clinical experts (neurological surgeons) with several years of experience in spine surgery and afterwards compared with the automatic segmentation results of the proposed scheme yielding an average Dice Similarity Coefficient (DSC) of 90.97±2.2%.