This volume contains the papers presented at the Scandinavian Conference on Image Analysis, SCIA 2009, which was held at the Radisson SAS Scandinavian Hotel, Oslo, Norway, June 15-18. SCIA 2009 was the 16th in the biennial series of conferences, which has been organized in turn by the Scandinavian countries Sweden, Finland, D- mark and Norway since 1980. The event itself has always attracted participants and author contributions from outside the Scandinavian countries, making it an international conference. Theconferenceincludedafulldayoftutorialsand?vekeynotetalksprovided by world-renowned experts. The program covered high-quality scienti?c cont- butions within image analysis, human and action analysis, pattern and object recognition, colorimagingandquality, medicalandbiomedicalapplications, face andheadanalysis, computer vision, andmultispectralcoloranalysis. The papers werecarefully selected based on at least two reviews. Among 154 submissions 79 wereaccepted, leadingtoanacceptancerateof51%. SinceSCIAwasarrangedas a single-track event, 30 papers were presented in the oral sessions and 49 papers were presented in the poster sessions. A separate session on multispectral color science was organized in cooperation with the 11th Symposium of Multispectral Color Science (MCS 2009). Since 2009 was proclaimed the "International Year of Astronomy" by the United Nations General Assembly, the conference also contained a session on the topic "Imageand PatternAnalysis in Astronomyand Astrophysics. " SCIA has a reputation of having a friendly environment, in addition to hi- quality scienti?c contributions. We focused on maintaining this reputation, by designing a technical and social program that we hope the participants found interesting and inspiring for new research ideas and network extensions. We thank the authors for submitting their valuable work to SCIA.

The key component in forecasting demand and consumption of resources in a supply network is an accurate prediction of real-valued time series. Indeed, both service interruptions and resource waste can be reduced with the implementation of an effective forecasting system. Significant research has thus been devoted to the design and development of methodologies for short term load forecasting over the past decades. A class of mathematical models, called Recurrent Neural Networks, are nowadays gaining renewed interest among researchers and they are replacing many practical implementations of the forecasting systems, previously based on static methods. Despite the undeniable expressive power of these architectures, their recurrent nature complicates their understanding and poses challenges in the training procedures. Recently, new important families of recurrent architectures have emerged and their applicability in the context of load forecasting has not been investigated completely yet. This work performs a comparative study on the problem of Short-Term Load Forecast, by using different classes of state-of-the-art Recurrent Neural Networks. The authors test the reviewed models first on controlled synthetic tasks and then on different real datasets, covering important practical cases of study. The text also provides a general overview of the most important architectures and defines guidelines for configuring the recurrent networks to predict real-valued time series.