Search

Highlights • An automatic generic method to measure garments from a single image is proposed. • The method is easily extensible to new types of garments. • We learn a Conditional Random Field for contour labeling for each garment type. • A Lasso regressor is learned which estimates the longitudinal measures of interest. • Mean absolute error is 1.17 and 1.22 cm for 130 jackets and 98 pants. Abstract Clothing is still manually manufactured for the most part nowadays, resulting in discrepancies between nominal and real dimensions, and potentially ill-fitting garments. Hence, it is common in the apparel industry to manually perform measures at preshipment time. We present an automatic method to obtain such measures from a single image of a garment that speeds up this task. It is generic and extensible in the sense that it does not depend explicitly on the garment shape or type. Instead, it learns through a probabilistic graphical model to identify the different contour parts. Subsequently, a set of Lasso regressors, one per desired measure, can predict the actual values of the measures. We present results on a dataset of 130 images of jackets and 98 of pants, of varying sizes and styles, obtaining 1.17 and 1.22 cm of mean absolute error, respectively. [ABSTRACT FROM AUTHOR]

Kidney stone formation is a common disease and the incidence rate is constantly increasing worldwide. It has been shown that the classification of kidney stones can lead to an important reduction of the recurrence rate. The classification of kidney stones by human experts on the basis of certain visual color and texture features is one of the most employed techniques. However, the knowledge of how to analyze kidney stones is not widespread, and the experts learn only after being trained on a large number of samples of the different classes. In this paper we describe a new device specifically designed for capturing images of expelled kidney stones, and a method to learn and apply the experts knowledge with regard to their classification. We show that with off the shelf components, a carefully selected set of features and a state of the art classifier it is possible to automate this difficult task to a good degree. We report results on a collection of 454 kidney stones, achieving an overall accuracy of 63% for a set of eight classes covering almost all of the kidney stones taxonomy. Moreover, for more than 80% of samples the real class is the first or the second most probable class according to the system, being then the patient recommendations for the two top classes similar. This is the first attempt towards the automatic visual classification of kidney stones, and based on the current results we foresee better accuracies with the increase of the dataset size. [ABSTRACT FROM AUTHOR]

Network virtualisation promises to lead to better manageability of the future Internet by allowing for adaptable sharing of physical network resources among different virtual networks. However, the sharing of resources is not trivial as virtual nodes and links should first be mapped onto substrate nodes and links, and thereafter the allocated resources managed throughout the lifetime of the virtual network. In this paper, we design and evaluate reinforcement learning-based neuro-fuzzy algorithms that perform dynamic, decentralised and coordinated self-management of substrate network resources. The objective is to achieve better efficiency in the utilisation of substrate network resources while ensuring that the quality of service requirements of the virtual networks are not violated. The proposed algorithms are evaluated through comparisons with a Q-learning-based approach as well as two static resource allocation schemes. [ABSTRACT FROM AUTHOR]