H2020Индивидуална стипендия2016–2018

HiDDaProTImA · High-dimensional data processing: from theory to imaging applications

„Хоризонт 2020“ — Действия „Мария Склодовска-Кюри“

Период: 2016-02-01 → 2018-01-31
Финансиране от ЕС: 183 455 €
Участници: 1
Схема: MSCA-IF

Линиите свързват координатора с партньорите.

Накратко на български

Математическите методи за обработка на сложни данни помагат за по-точно разпознаване на лица и сегментиране на видеоклипове. Тези алгоритми подобряват качеството на изображенията и работата на ендоскопите за ранно откриване на рак на хранопровода.

Този кратък обзор е генериран от изкуствен интелект

Кратко обяснение, генерирано от езиков модел по текста на CORDIS. Оригиналът е по-долу.

Резултати накратко

High-dimensional data processing: from theory to imaging applications

The research work carried out within the project HiDDaProTImA had the objective of studying fundamental limits on how information can be extracted and processed from high-dimensional data, and to design methods and algorithms able to achieve such fundamental limits. On leveraging probabilistic and deterministic mathematical frameworks to model high-dimensional data, we aimed at providing answers to the following research questions: 1. What is the minimum number of features that we need to extract from high-dimensional data in order to reliably extract information? And how to extract such information? 2. What is the advantage represented by the presence of additional side information in processing high-dimensional data? And how should we optimally capture such side information? 3. What is the optimal way to learn dictionaries to represent? What is the interplay between dictionary learning and optimizing feature extraction? Although the answers to such research questions have an important impact on different application fields involving information processing of high-dimensional data, the focus of the work carried out within the project HiDDAProTImA has been that of imaging applications. In this way, the results derived within the project have allowed to gauge more effectively the number of measurements and features needed to operate different tasks in imaging, as for example, video segmentation and face recognition, providing at the same time useful feature design methods. Moreover, we have proposed a way to increase the quality of images obtained from compressive imaging devices by leveraging side information. Finally, we have derived a mathematical framework to improve the performance of fibre bundles used for holographic endoscopy for early oesophageal cancer detection, by allowing for fast calibration and by enhancing image quality as well as discriminative power between healthy tissues and lesions.

Текст от CORDIS, на английски · Данни: CORDIS, © Европейски съюз

Цел на проекта

The unstoppable increase in the volume of data stored, transmitted and interpreted by fixed and mobile devices strongly calls for the study of efficient solutions in processing the information contained in high-dimensional signals. Such need has been reflected in the recent flourishing of research efforts from the statistics, machine learning, computer science and signal processing communities. Within this multidisciplinary research ground, the proposed project will address the central question that can be formulated as -- what is the maximum level of information contained in large datasets that we can process from a small number of features, and how is it possible to achieve such limit in practice?Recent advances in information processing have demonstrated that a promising mathematical tool to tackle this question is represented by the Bayesian approach, in which statistical models inferred from training samples accurately describe the data. In fact, the Bayesian framework offers fundamental advantages in modeling high-dimensional signals in terms of mathematical tractability of performance limits as well as enhanced capabilities in information processing. Beyond the study of performance limits, the proposed project will involve case studies and applications in image processing. The researcher will be able to establish active collaborations with various research groups, in different department of Cambridge University, that test their research results on actual imaging devices.This project will also form the proposer to his future independent research activity and it will provide him with new mathematical skills and practical implementation expertise with actual imaging systems. On the other hand, Cambridge University will benefit from the cross pollination of ideas brought by the researcher and his collaborators in top institutions in Europe and the US.

Оригинален текст от CORDIS (на английски).

Участници

THE CHANCELLOR MASTERS AND SCHOLARS OF THE UNIVERSITY OF CAMBRIDGE · CAMBRIDGEКоординаторОбединеното кралство