Dr. Pierluigi Carcagni Profile

Dr. Pierluigi Carcagni

at National Research Council of Italy

SPIE Involvement:

Author

Publications (14)

Proceedings Article | 20 June 2021 Paper

An investigation on deep learning approaches for diatoms classification

Pierluigi Carcagni, Andouglas Goncalves da Silva, Pasquale Memmolo, Vittorio Bianco, Francesco Merola, Luiz Marcos Garcia Goncalves, Andouglas Silva, Pietro Ferraro, Cosimo Distante

Proceedings Volume 11785, 117850Q (2021) https://doi.org/10.1117/12.2593252

KEYWORDS: Water, Taxonomy, Oceanography, Holography, Environmental monitoring, Neural networks, Microscopy, Machine vision, Image classification, Holograms

Read Abstract +

Proceedings Article | 21 June 2019 Paper

Characterization of microplastics by holographic features for automatic detection in heterogeneous samples

V. Bianco, P. Memmolo, F. Merola, P. Carcagni, M. Paturzo, C. Distante, P. Ferraro

Proceedings Volume 11060, 110601E (2019) https://doi.org/10.1117/12.2527496

KEYWORDS: Oceanography, Holography, Water, Holograms, Sensors, Microscopy, Coherence imaging, Digital holography, Positron emission tomography, CCD image sensors

Read Abstract +

Proceedings Article | 21 June 2019 Presentation + Paper

Convolutional neural networks for recognition and segmentation of aluminum profiles

Pier Luigi Mazzeo, Arturo Argentieri, Federico De Luca, Paolo Spagnolo, Cosimo Distante, Marco Leo, Pierluigi Carcagnì

Proceedings Volume 11059, 110590S (2019) https://doi.org/10.1117/12.2525687

KEYWORDS: Image segmentation, Aluminum, Neural networks, Computer aided design, Data modeling, Convolutional neural networks, Solid modeling, Cameras, Network architectures, Feature extraction

Read Abstract +

Learning to automatically recognize objects in the real world is a very important and stimulating challenge. This work deals with the problem of detecting aluminium profiles within images, using hierarchical representations such as those based on deep learning methods. The use of regional CNN, a conceptually simple, flexible, and general framework for object instance segmentation, allows to exceed the previous state-of-the-art results. This approach efficiently detects objects in an image while simultaneously generating a high-quality segmentation mask for each instance. Neural network training uses ResNet networks of depth 50 or 101 layers. In particular, the training dataset consists of synthetic data generated by CAD files. The Dataset creation process is fundamental: experimental results show that trivial datasets lead to poor detection performance. A rich dataset, instead, including more complex images, allows the network to learn more and better guaranteeing excellent results. How to get more data, if you do not have more data? To get more data, we just need to make minor alterations such as flips, scale or rotations to existing dataset. This process is known as Data augmentation. The performance of the proposed system strongly depends on the dataset used for training and on the backbone architecture used. This why, adopting a strategy that generates a priori a very large dataset the time required to create the annotation file grows almost exponentially. The validation and test dataset, on the other hand, consists of real images captured by cameras. The distinctiveness of this work consists to train a deep neural network with synthetic data (aluminium CAD files) and verify if it on real data. Experiments show that the implementation of architecture, as described above, leads to good performance in automatic detection and classification. Future work will be addressed to improve the network training process together with the architecture, the algorithms and the dataset creation process. The latter is proved to be fundamental for the balance and optimization of the whole process. The way is to develop not much augmented datasets focusing on online data augmentation during network training.

Proceedings Article | 21 June 2019 Presentation + Paper

Identification and classification of biological micro-organisms by holographic learning

Pasquale Memmolo, Vittorio Bianco, Pierluigi Carcagnì, Andouglas Goncalves da Silva Junior , Luiz Marcos Garcia Goncalves, Francesco Merola, Melania Paturzo, Cosimo Distante, Pietro Ferraro

Proceedings Volume 11060, 110600H (2019) https://doi.org/10.1117/12.2527484

KEYWORDS: Digital holography, Holography, Holograms, Microorganisms, Intelligence systems, Feature extraction, Phase imaging, Machine learning, Image classification, Applied sciences

Read Abstract +

Proceedings Article | 21 June 2019 Presentation + Paper

How holographic imaging can improve machine learning

Pasquale Memmolo, Vittorio Bianco, Pierluigi Carcagnì, Francesco Merola, Melania Paturzo, Cosimo Distante, Pietro Ferraro

Proceedings Volume 11059, 1105908 (2019) https://doi.org/10.1117/12.2527480

KEYWORDS: Holography, Digital holography, Machine learning, Microscopy, Holograms, Microscopes, Intelligence systems, Refractive index, 3D image reconstruction, Digital imaging

Read Abstract +

Proceedings Article | 4 March 2019 Presentation + Paper

High-accuracy identification of micro-plastics by holographic microscopy enabled support vector machine

V. Bianco, P. Memmolo, F. Merola, P. Carcagni, C. Distante, P. Ferraro

Proceedings Volume 10887, 108870F (2019) https://doi.org/10.1117/12.2509515

KEYWORDS: Holography, Microscopy, Oceanography, Water, Machine learning, Holograms, Microscopes, Digital holography, Intelligence systems, Liquids

Read Abstract +

Proceedings Article | 21 June 2011 Paper

Autofocus laser system for multi-NIR scanning imaging of painting surfaces

R. Fontana, M. Barucci, P. Carcagnì, C. Daffara, E. Pampaloni, L. Pezzati

Proceedings Volume 8084, 808405 (2011) https://doi.org/10.1117/12.889487

KEYWORDS: Near infrared, Head, Scanners, 3D modeling, Imaging systems, Reflectivity, Diagnostics, Imaging spectroscopy, Composites, Infrared imaging

Read Abstract +

Proceedings Article | 7 July 2009 Paper

Noninvasive conoscopic holography-based device for artworks surface acquisition

P. Carcagnì, E. Cavallo, A. Della Patria, G. Gianfrate, L. Pezzati, R. Piccolo, P. Pingi

Proceedings Volume 7391, 73910Z (2009) https://doi.org/10.1117/12.828209

KEYWORDS: Mirrors, Holography, Microscopy, Geometrical optics, Crystals, Laser engraving, 3D modeling, Circular polarizers, Sensors, Calibration

Read Abstract +

Proceedings Article | 19 July 2007 Paper

Multispectral imaging of paintings: instrument and applications

Claudio Bonifazzi, Pierluigi Carcagnì, Andrea Della Patria, Raffaella Fontana, Marinella Greco, Maria Mastroianni, Marzia Materazzi, Enrico Pampaloni, Luca Pezzati, Afra Romano

Proceedings Volume 6618, 661816 (2007) https://doi.org/10.1117/12.726113

KEYWORDS: Principal component analysis, Multispectral imaging, Spectral resolution, Image analysis, Reflectivity, Sensors, Cameras, Imaging systems, Spatial resolution, Visible radiation

Read Abstract +

Proceedings Article | 19 July 2007 Paper

Multi-spectral IR reflectography

Raffaella Fontana, Davide Bencini, Pierluigi Carcagnì, Marinella Greco, Maria Mastroianni, Marzia Materazzi, Enrico Pampaloni, Luca Pezzati

Proceedings Volume 6618, 661813 (2007) https://doi.org/10.1117/12.726096

KEYWORDS: Scanners, Infrared imaging, Near infrared, Light sources and illumination, Infrared radiation, Sensors, Principal component analysis, Transparency, Diagnostics, Head

Read Abstract +

Proceedings Article | 13 July 2007 Paper

Three-dimensional survey of paint layer

Enrico Pampaloni, Roberto Bellucci, Pierluigi Carcagni, Antonella Casaccia, Raffaella Fontana, Maria Chiara Gambino, Roberta Piccolo, Paolo Pingi, Luca Pezzati

Proceedings Volume 6618, 66180F (2007) https://doi.org/10.1117/12.726105

KEYWORDS: Floods, Image filtering, Ranging, Data analysis, Crystals, Morphological analysis, Diagnostics, 3D modeling, Profilometers, Optics manufacturing

Read Abstract +

Proceedings Article | 17 January 2006 Paper

A scanning device for multispectral imaging of paintings

Claudio Bonifazzi, Pierluigi Carcagnì, Andrea Della Patria, Stefano Ferriani, Raffaella Fontana, Marinella Greco, Maria Mastroianni, Marzia Materazzi, Enrico Pampaloni, Afra Romano

Proceedings Volume 6062, 60620M (2006) https://doi.org/10.1117/12.641668

KEYWORDS: Principal component analysis, Multispectral imaging, Reflectivity, Sensors, Imaging devices, Calibration, Spatial resolution, Reflection, Cameras, Image analysis

Read Abstract +

Proceedings Article | 18 August 2005 Paper

Optical micro-profilometry for archaeology

Pierluigi Carcagni, Claudia Daffara, Raffaella Fontana, Maria Chiara Gambino, Maria Mastroianni, Cinazia Mazzotta, Enrico Pampaloni, Luca Pezzati

Proceedings Volume 5857, 58570F (2005) https://doi.org/10.1117/12.612527

KEYWORDS: 3D image processing, 3D modeling, Photography, Corrosion, Statistical analysis, Surface roughness, 3D metrology, Data acquisition, Image processing software, Cultural heritage

Read Abstract +

Proceedings Article | 12 August 2005 Paper

Spectral and colorimetric characterisation of painted surfaces: a scanning device for the imaging analysis of paintings

Pierluigi Carcagni, Andrea Della Patria, Raffaella Fontana, Marinella Greco, Maria Mastroianni, Marzia Materazzi, Enrico Pampaloni, Luca Pezzati, Roberta Piccolo

Proceedings Volume 5857, 58570T (2005) https://doi.org/10.1117/12.612565

KEYWORDS: Multispectral imaging, Sensors, Imaging systems, Reflectivity, RGB color model, Scanners, Imaging devices, Spectroscopy, Reflection, Ceramics

Read Abstract +

Showing 5 of 14 publications

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Keywords/Phrases

Search In:

Publication Years