Angelo Chianese

Foveated shot detection for video segmentation

We view scenes in the real world by moving our eyes three to four times each second and integrating information across subsequent fixations (foveation points). By taking advantage of this fact, in this paper we propose an original approach to partitioning of a video into shots based on a foveated representation of the video. More precisely, the shot-change detection method is related to the computation, at each time instant, of a consistency measure of the fixation sequences generated by an ideal observer looking at the video. The proposed scheme aims at detecting both abrupt and gradual transitions between shots using a single technique, rather than a set of dedicated methods. Results on videos of various content types are reported and validate the proposed approach.

Recovering dynamic information from static handwriting

It is generally agreed that the advantage of on-line character recognition methods with respect to off-line ones mostly relies on the availability of dynamic information. This mainly concerns the order in which the strokes forming characters have been drawn. In this paper we present and discuss a method which attempts, in the off-line case, to recover part of the lost script dynamics. The method makes it possible to reconstruct one of the most likely trajectories followed by the writer while drawing characters. It is based on a suitable implementation of good continuity criteria which take into account direction, length and width of the strokes making up characters. The algorithm either subdivides or unfolds the digital ribbon forming isolated characters as well as groups of connected characters, by solving the ambiguities which arise at every joint. Experimental results are reported and discussed.

The Talking Museum Project

Abstract In this paper, we present an ongoing project, named Talking Museum and developed within DATABENC - a high technology district for Cultural Heritage management. The project exploits the Internet of Things technologies in order to make objects of a museum exhibition able to “talk” during users’ visit and capable of automatically telling their story using multimedia facilities. In particular, we have deployed in the museum a particular Wireless Sensor Network that, using Bluetooth technology, is able to sense the surrounding area for detecting user devices’ presence. Once a device has been detected, the related MAC address is retrieved and a multimedia story of the closest museum objects is delivered to the related user. Eventually, proper multimedia recommendation techniques drive users towards other objects of possible interest to facilitate and make more stimulating the visit. As case of study, we show an example of Talking museum as a smart guide of sculptures’ art exhibition within the Maschio Angioino castle, in Naples (Italy).

Smart environments and Cultural Heritage: a novel approach to create intelligent cultural spaces

The relationship between cultural heritage domain and new technologies has always been complex, dialectical and often inspired by the human desire to induce these spaces not created for that purpose, to pursue technological trends, eventually offering to the end-users devices and innovative technologies that could become a ‘dead weight’ during their cultural experiences. However, by means of innovative technological applications and location-based services it is possible to shorten the distance between cultural spaces and their visitors, nowadays determined by the purely aesthetic and essentially passive fruition of cultural objects. This paper presents the design and implementation of a novel multipurpose system for creating single smart spaces (), a new concept of intelligent environment, that relies on innovative sensors board named smart crickets and an ad hoc proximity strategy; by following the Internet of Things paradigm the proposed system is able to transform a cultural space in a smart cultural environment to enhance the enjoyment and satisfaction of the involved people. To assess the effectiveness of our solution, we have experienced two real case studies, the first one situated within an art exhibition (indoor), and the second one concerning an historical building (outdoor). In this way, technology can become a mediator between visitors and fruition, an instrument of connection between people, objects and spaces to create new social, economic and cultural opportunities.

Designing a Smart Museum: When Cultural Heritage Joins IoT

The adoption of the Internet of Things (IoT) paradigm constitutes the basic building block to progress towards unified ICT platforms for a variety of applications within the large framework of the smart cities. Unfortunately, designing a general architecture for IoT is still a very complex challenge, since in such system may be involved several devices, link layer technologies and services. Cultural Heritage represents a worldwide resource of inestimable value and it gains more and more importance when embedded into the digital ecosystem of a smart city. In this paper we focus specifically to design a IoT architecture that is able to support the designing of a smart museum, a static cultural space that becomes intelligent thanks to the definition of an innovative model of sensors and services. Furthermore, the paper will present and discuss a real case of study, placed in a temporary art exhibition of sculptures in the Maschio Angioino Castle, located in Naples, Italy.

Computer aided detection of microcalcifications in digital mammograms

Microcalcification detection is widely used for early diagnosis of breast cancer. Nevertheless, mammogram visual analysis is a complex task for expert radiologists. In this paper, we present a new method for computer aided detection of microcalcifications in digital mammograms. The detection is performed on the wavelet transformed image. The calcifications are separated from the background by exploiting the evaluation of Renyis information at the different decomposition levels of the wavelet transform. Experiments are performed on a standard and publicly available dataset and the results are evaluated with respect to recent achievements reported in the literature.

A multimedia recommender integrating object features and user behavior

Despite the great amount of work done in the last decade, retrieving information of interest from a large multimedia repository still remains an open issue. In this paper, we propose an intelligent browsing system based on a novel recommendation paradigm. Our approach combines usage patters with low-level features and semantic descriptors in order to predict users’ behavior and provide effective recommendations. The proposed paradigm is very general and can be applied to any type of multimedia data. In order to make the recommender system even more flexible, we introduce the concept of multichannel browser, i.e. a browser that allows concurrent browsing of multiple media channels. We implemented a prototype of the proposed system and tested the effectiveness of our approach in a virtual museum scenario. Experimental results have proved that the system greatly enhances users’ experience, thus encouraging further research in this direction.

Small target detection using wavelets

Presents a method for the detection of small objects embedded in a noisy background. The detection is performed on the wavelet transformed image. After a preliminary de-noising pass, the objects are separated from background by exploiting the evaluation of Renyis information at the different decomposition levels of the wavelet transform. We apply the proposed technique to detect microcalcifications in digital mammographic images.

A smart system to manage the context evolution in the Cultural Heritage domain

Model the context evolution by means of a graph approach.Design a Context Evolution System (CES) to manage the context evolution and the consequently tailoring of data and services.Improve user experience by means of this kind of system.Our apporach is suitable within the Cultural Heritage domain. Nowadays intelligent and pervasive environments are characterized by a great number of devices and sensors that develop continuously and capture enormous amounts of data. Designing a context-aware system able to provide the most tailored services to users according to their behaviors, preferences and needs is still a research challenge. In such environments, although the context is very complex, dynamic and full of data captured and produced, users aspire to automatically receive contextualized services. The Cultural Heritage domain represents a domain where exchanged and produced data can be opportunely exploited by a set of applications and services in order to transform a static space into a smart environment. In this perspective, this paper presents a context-aware system named Context Evolution System (CES) able to represent and manage the evolution of the context through its instances; such an evolution is driven by occurring events and opportunely modeled by a graph structure. To assess the proposed solution, a Cultural Heritage case study of a real temporary art exhibition named the Beauty or the Truth and located in Naples (Italy) is presented and discussed.

Context-sensitive queries for image retrieval in digital libraries

In this paper we show how to achieve a more effective Query By Example processing, by using active mechanisms of biological vision, such as saccadic eye movements and fixations. In particular, we discuss the way to generate two fixation sequences from a query image Iq and a test image It of the data set, respectively, and how to compare the two sequences in order to compute a similarity measure between the two images. Meanwhile, we show how the approach can be used to discover and represent the hidden semantic associations among images, in terms of categories, which in turn drive the query process.