Stefano Saetta

Automatic classification of granite tiles through colour and texture features

This paper is about the development of an expert system for automatic classification of granite tiles through computer vision. We discuss issues and possible solutions related to image acquisition, robustness against noise factors, extraction of visual features and classification, with particular focus on the last two. In the experiments we compare the performance of different visual features and classifiers over a set of 12 granite classes. The results show that classification based on colour and texture is highly effective and outperforms previous methods based on textural features alone. As for the classifiers, Support Vector Machines show to be superior to the others, provided that the governing parameters are tuned properly.

Internal combustion engine combined heat and power plants: Case study of the University of Perugia power plant

Abstract A performance and economic analysis of an existing combined heat and power plant with an internal combustion engine and district heating for the Faculty of Engineering of the University of Perugia is presented. Results of the first 15 months of operation are shown and discussed with reference to daily performance of the combined heat and power plant, which shows how electric efficiency is only slightly affected by ambient temperature. A comparison of evaluation indexes for cogeneration plants is made with particular attention to the energy index ( EI ) which is used by Italian legislation as an evaluation parameter to decide if a combined heat and power plant can have access to financial benefits. A cost–benefits analysis based on the first year of operation was made to decide eventual changes in heat and power management, in order to reduce pay-back period and increase the internal rate of return of the investment.

Performance analysis of colour descriptors for parquet sorting

In this paper we consider the problem of colour-based sorting hardwood parquet slabs into lots of similar visual appearance. As a basis for the development of an expert system to perform this task, we experimentally investigate and compare the performance of various colour descriptors (i.e.: soft descriptors, percentiles, marginal histograms and 3D histogram), and colour spaces (i.e.: RGB, HSV and CIE Lab). The results show that simple and compact colour descriptors, such as the mean of each colour channel, are as accurate as more complicated features. Likewise, we found no statistically significant difference in the accuracy attainable through the colour spaces considered in the paper. Our experiments also show that most methods are fast enough for real-time processing. The results suggest the use of simple statistical descriptors along with RGB data as the best practice to approach the problem.

The innovative model of the Virtual Development Office for collaborative networked enterprises: the GPT network case study

The paper presents one of the most interesting collaborative networked organisations in Italy, namely Gruppo Poligrafico Tiberino (GPT), the first organisation that adopts the governance model with the Virtual Development Office (VDO) structure. The VDO is an innovative model that introduces products/services innovation through collaboration between companies, with a particular focus on small and medium enterprises (SMEs). In effect, the existing forms of collaboration are evolving towards the direction of extending the classical collaboration fields of supply chains including phases like product and service development. However, when collaboration is established exclusively among SMEs, the introduction of new products/services becomes much more difficult. This is due to the lack of the actions of a leader firm, that is, a big company that is able to innovate. The VDO model is introduced to overcome this limit, and to stimulate innovation in collaborative networks of SMEs. GPT network is constituted by 21 companies belonging to the paper converting, packaging and logistics sectors. The nature of the collaboration is based on a long-term strategy vision, giving to the network more competitive advantages, with respect to the classical collaborative alliances in Italy, such as industrial districts, cooperatives, consortiums or temporary associations. Started from a national research project, currently it is a very fast growing up reality; the significant results achieved and the strong interests coming from Institutions, Ministries and Universities make GPT a real success both under the industrial and the academic perspectives.

A sequential machine vision procedure for assessing paper impurities

We present a sequential, two-step procedure based on machine vision for detecting and characterizing impurities in paper. The method is based on a preliminary classification step to differentiate defective paper patches (i.e., with impurities) from non-defective ones (i.e., with no impurities), followed by a thresholding step to separate the impurities from the background. This approach permits to avoid the artifacts which occur when thresholding is applied to paper samples that contain no impurities. We discuss and compare different solutions and methods to implement the procedure and experimentally validate it on a datasets of 11 paper classes. The results show that a marked increase in detection accuracy can be obtained with the two-step procedure in comparison with thresholding alone.

Automatic Characterization of the Visual Appearance of Industrial Materials through Colour and Texture Analysis: An Overview of Methods and Applications

We present an overview of methods and applications of automatic characterization of the appearance of materials through colour and texture analysis. We propose a taxonomy based on three classes of methods (spectral, spatial, and hybrid) and discuss their general advantages and disadvantages. For each class we present a set of methods that are computationally cheap and easy to implement and that was proved to be reliable in many applications. We put these methods in the context of typical industrial environments and provide examples of their application in the following tasks: surface grading, surface inspection, and content-based image retrieval. We emphasize the potential benefits that would come from a wide implementation of these methods, such as better product quality, new services, and higher customer satisfaction.

A web-based simulation game as a learning tool for the design process of complex systems

While relational simulation games have been widely used for learning activities in areas such as business, management and communication, their development in the engineering field is still very limited. In this paper a web-based simulation game was designed in order to fill this existing gap in the development of relational simulation games related to engineering aspects and in particular to the design process of complex systems. An evaluation of a first web trial competition, carried out by questionnaires, shows a satisfactory achievement of the proposed learning tool objectives.

A decomposition approach for the performance analysis of a serial multi-echelon supply chain

Over the last decade, supply chain coordination has attracted much attention in the context of industrial logistics systems, because of the role played in production support logistics. There is a growing interest in the analysis and measurement of performances, because performance analysis allows us to build supporting decision tools for the design, planning and management of the supply chain. This paper presents an analytical approach for performance analysis based on a decomposition principle. The approach is applied to a serial supply chain that consists of two levels of suppliers, a production plant and a distribution centre, and operates as a pull system. This configuration is typical for bulk materials such as grain. The method allows us to approximately calculate performance indicators (such as customer satisfaction and inventory levels) taking into account all the interactions between the different echelons of the supply chain. The accuracy of the approximations is confirmed by the results obtained via a simulation model. Numerical analysis allows us to outline interesting and non-intuitive behaviour of the performance indicators for different stages of the supply chain.

Evaluating How Potential Pool of Partners Can Join Together in Different Types of Long Term Collaborative Networked Organizations

The considerable benefits brought up by strategic alliances and diverse types of long term Collaborative Networked Organizations (CNOs) are nowadays widely recognized. There is an increasing demand in the industrial world for concretely implement new forms of collaborations. For example, demand often comes from pre-existent form of clusters or local productive arrangements, that want to evolve to more efficient forms of collaboration, or from small and medium enterprises that are facing a crisis, and look at collaboration with other enterprises as almost the last chance to survive. In general, variety of motivations in collaborating implies variety of missions of potential collaborations, that in turn requires the choice of an appropriate form of Collaborative Network aligned to the mission statement. This paper addresses the problem to define a methodology for analyzing potential pool of partners and for identifing the mission, the form, the governance structure and the value drivers of long term strategic alliance that would bring highest benefits to the partners. Three different forms of CNOs are considered: the Virtual organizations Breeding Environment (VBE), the Virtual Development Office (VDO) and the T-Holding.

A Framework for Evaluating Enterprise Network Performances

Globalization has entailed the necessity for small businesses to join skills and forces together in order to compete in the new economy. New industrial collaboration forms are evolving during last years, indicating with different degree of success the achievement of the first goal of the alliances: the competitiveness of the partners involved within. The necessity for new management methodologies for these new environments are nowadays strongly emerging. Among them, the performance measurement of the network businesses is still something not well discussed in literature. The deep understanding of the network results in terms of performance measurement is one of the most value adding activities within the collaborative environment. This article proposes an assessment of the network performances, through an auto-evaluation questionnaire submitted to the partners of a network with the Virtual Development Office (VDO) structure. First qualitative and quantitative results follow.