Search results for "Image"

Extracting Touristic Information from Online Image Collections

2012

In this paper, we present a Geographical Information Retrieval system, which aims to automatically extract and analyze touristic information from photos of online image collections (in our case of study Flickr). Our system collect all the photos, and the related information, that are associated to a specific city. We then use Google Maps service to geolocate the retrieved photos, and finally we analyze geo-referenced data to obtain our goals: 1) determining and locating the most interesting places of the city, i.e. the most visited locations, and 2) reconstructing touristic routes of the users visiting the city. Information is filtered by using a set of constraints, which we apply to select…

Dealing with reconstruction problems: two cases study

Reconstruction problems are always included in a computer vision system as one of the key step toward the recognition of a scene. There are hierarchies of reconstruction that go from pixels to regions in the lower level, and from patches to objects in higher steps. The success of the reconstruction phase de-pends on several factors: the selection of "suitable" features, the matching function, the linking strategy. I this paper we show some of problems and solutions in two different contexts: the 3D reconstruction from cloud of points representing fragments of archeological finding, and the mosaicing from sea bed video frames. Preliminary results show that in both cases the accuracy is satis…

Ecological Invitation to Engage with Public Displays

2018

Interactive public displays pose several research issues, which include display blindness and interaction blindness. In this paper, we shortly introduce our idea of a sound-based system to overcome the display blindness, and some experiments that we are carrying out in order to test its effectiveness.

CubeHarmonic: A new musical instrument based on Rubik{'}s cube with embedded motion sensor

2019

A contemporary challenge involves scientific education and the connection between new technologies and the heritage of the past. CubeHarmonic (CH) joins novelty and tradition, creativity and edu- cation, science and art. It takes shape as a novel musical instrument where magnetic 3D motion tracking technology meets musical per- formance and composition. CH is a Rubik’s cube with a note on each facet, and a chord or chord sequence on each face. The posi- tion of each facet is detected through magnetic 3D motion tracking. While scrambling the cube, the performer gets new chords and new chord sequences. CH can be used to compose, improvise,1 and teach music and mathematics (group theory, permu…

An evaluation of recent local image descriptors for real-world applications of image matching

2019

This paper discusses and compares the best and most recent local descriptors, evaluating them on increasingly complex image matching tasks, encompassing planar and non-planar scenarios under severe viewpoint changes. This evaluation, aimed at assessing descriptor suitability for real-world applications, leverages the concept of approximated overlap error as a means to naturally extend to non-planar scenes the standard metric used for planar scenes. According to the evaluation results, most descriptors exhibit a gradual performance degradation in the transition from planar to non-planar scenes. The best descriptors are those capable of capturing well not only the local image context, but als…

3D Map Computation from Historical Stereo Photographs of Florence

2018

The analysis of early photographic sources is fundamental for documenting and understanding the evolution of a city so rich in history and art as Florence. Indeed, by the 1860s several photographers used to work in town, and their images (often obtained through stereoscopic set-ups) can help us to reconstruct Florence in 3D as it was by the time of the Italian unification. The first and most delicate part of such reconstruction process is the computation of disparity maps from the historical stereo pairs. This is a very challenging task for fully-automatic computer vision algorithms, since XIX century photographs are affected by several problems—ranging from superficial damages to asynchron…

Is There Anything New to Say About SIFT Matching?

2020

SIFT is a classical hand-crafted, histogram-based descriptor that has deeply influenced research on image matching for more than a decade. In this paper, a critical review of the aspects that affect SIFT matching performance is carried out, and novel descriptor design strategies are introduced and individually evaluated. These encompass quantization, binarization and hierarchical cascade filtering as means to reduce data storage and increase matching efficiency, with no significant loss of accuracy. An original contextual matching strategy based on a symmetrical variant of the usual nearest-neighbor ratio is discussed as well, that can increase the discriminative power of any descriptor. Th…

Editorial for special issue “fine art pattern extraction and recognition”

2021

: Cultural heritage, especially the fine arts, plays an invaluable role in the cultural, historical, and economic growth of our societies [...].

Retinal image synthesis through the least action principle

2020

Eye fundus image analysis is a fundamental approach in medical diagnosis and follow-up ophthalmic diagnostics. Manual annotation by experts needs hard work, thus only a small set of annotated vessel structures is available. Examples such as DRIVE and STARE include small sets for training images of fundus image benchmarks. Moreover, there is no vessel structure annotation for a number of fundus image datasets. Synthetic images have been generated by using appropriate parameters for the modeling of vascular networks or by methods developing deep learning techniques and supported by performance hardware. Our methodology aims to produce high-resolution synthetic fundus images alternative to the…

Medical image registration: Interpolations, similarities and optimizations strategies

2010

This paper presents a study conducted for evaluating different interpolation schemes, similarity metrics and optimization algorithms for the purpose of volumetric medical image registration. Each technique has been implemented to be plugged in a modular system. Rotation, translation and scale error has been measured to obtain a performance evaluation for all of the combinations of the considered techniques. Several experimental tests were conducted for validation both on synthetic and real datasets providing an exhaustive overview of the various strategies used.