O klasifikaciji slik v ne-enolično določljive razrede

Image classification is one of the most basic and frequently addressed computer vision tasks. The usual formulation of this tasks requires classification of an image into the one of several possible classes. The most common metric for measuring the classifier’s performance is classification accuracy, defined as a percentage of correctly classified images. However, such formalisation of the classification problem relies on a strong assumption that for every image a category is uniquely identifiable and assigned by the domain expert. In this paper we address scenarios where this assumption does not hold. In particular, we present an analysis of the results obtained by the convolutional neural network and twelve participants who were tasked to classify the images of planks into eight classes and discuss the label ambiguity problem.