Zobrazeno 1 - 10
of 13
pro vyhledávání: '"Konstantina Kottari"'
Publikováno v:
IEEE Transactions on Cognitive and Developmental Systems. 12:588-600
In this article, we describe an approach for the problem of fall detection among the several other everyday activities in indoor environment, using three uncalibrated fisheye cameras. The proposed methodology requires the input segmented silhouettes
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7d1527383f06202c93bbd69395735f6e
https://doi.org/10.1109/tcds.2019.2948786
https://doi.org/10.1109/tcds.2019.2948786
Autor:
Kostas Delibasis, Spiros V. Georgakopoulos, Konstantina Kottari, Vassilis P. Plagianakos, Ilias Maglogiannis
Publikováno v:
Neural Computing and Applications. 31:1805-1822
In this work, we focus in the analysis of dermoscopy images using convolutional neural networks (CNNs). More specifically, we investigate the value of augmenting CNN inputs with the response of mid-level computer vision filters, using the traditional
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c0692461f473d21679869358c1ca1652
https://doi.org/10.1007/s00521-018-3711-y
https://doi.org/10.1007/s00521-018-3711-y
Autor:
Kostas Delibasis, Vassilis P. Plagianakos, Ilias Maglogiannis, Spiros V. Georgakopoulos, Konstantina Kottari
Publikováno v:
Neurocomputing. 280:23-31
Convolutional neural networks (CNNs) are used frequently in several computer vision applications. In this work, we present a methodology for pose classification of binary human silhouettes using CNNs, enhanced with image features based on Zernike mom
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::471efa10720a4f2124fcfce4b34bd819
https://doi.org/10.1016/j.neucom.2017.08.071
https://doi.org/10.1016/j.neucom.2017.08.071
Publikováno v:
Multimedia Tools and Applications. 77:9307-9324
This work proposes a fully automated approach for vision-based quality control of manufactured metal rods. The proposed approach is able to detect the main axis of the rod and calculate its curvature, versus specifications. The proposed algorithm uti
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b22470d98bff691ec6b15832072b7148
https://doi.org/10.1007/s11042-017-4891-7
https://doi.org/10.1007/s11042-017-4891-7
Autor:
Vassilis P. Plagianakos, Ilias Maglogiannis, Konstantinos K. Delibasis, Konstantina Kottari, Spiros V. Georgakopoulos
Publikováno v:
Integrated Computer-Aided Engineering. 23:185-199
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ca04a61a9369583abce1d4e44c8a1c50
https://doi.org/10.3233/ica-160511
https://doi.org/10.3233/ica-160511
Autor:
Konstantina Kottari, Vassilis P. Plagianakos, Ilias Maglogiannis, Spiros V. Georgakopoulos, Kostas Delibasis
Publikováno v:
Artificial Neural Networks and Machine Learning – ICANN 2018 ISBN: 9783030014179
ICANN (1)
ICANN (1)
Convolutional Neural Networks (CNNs) have been proven very effective in image classification and object recognition tasks, often exceeding the performance of traditional image analysis techniques. However, training a CNN requires very extensive datas
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c64d79a017f0d975c9f11a9c2a1d8c5e
https://doi.org/10.1007/978-3-030-01418-6_19
https://doi.org/10.1007/978-3-030-01418-6_19
Autor:
Kostas Delibasis, Vassilis P. Plagianakos, Ilias Maglogiannis, Spiros V. Georgakopoulos, Konstantina Kottari
Publikováno v:
Engineering Applications of Neural Networks ISBN: 9783319651712
EANN
EANN
In this work, we report the use of convolutional neural networks for the detection of malignant melanomas against nevus skin lesions in a dataset of dermoscopic images of the same magnification. The technique of transfer learning is utilized to compe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e5a90d7386a8036d5e98a2ca39d89b9a
https://doi.org/10.1007/978-3-319-65172-9_34
https://doi.org/10.1007/978-3-319-65172-9_34
Publikováno v:
2016 IEEE International Conference on Imaging Systems and Techniques (IST).
Reconstructing shape from silhouettes is an interesting topic in computer vision. In the case of projective (pinhole) cameras, this task has been solved with several variations. The increasing use of omnidirectional cameras, due to their apparent adv
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f1857ecdd42dccbdc1758055b25cc66d
https://doi.org/10.1109/ist.2016.7738213
https://doi.org/10.1109/ist.2016.7738213
Publikováno v:
2016 IEEE International Conference on Imaging Systems and Techniques (IST).
This work proposes a fully automated approach for vision-based quality control of manufactured metal rods. The proposed approach is able to detect the features of the rod (holes) and calculate the curvature of the object versus specifications. The pr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7e9c4d1f364781cb5d41e44093595716
https://doi.org/10.1109/ist.2016.7738263
https://doi.org/10.1109/ist.2016.7738263
Autor:
Vassilis P. Plagianakos, Ilias Maglogiannis, Kostas Delibasis, Spiros V. Georgakopoulos, Konstantina Kottari
Publikováno v:
IFIP Advances in Information and Communication Technology ISBN: 9783319449432
AIAI
AIAI
In this work, we present a methodology for pose classification of silhouettes using convolutional neural networks. The training set consists exclusively from the synthetic images that are generated from three-dimensional (3D) human models, using the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::eb44ff462498bad0b995085fae1451e6
https://doi.org/10.1007/978-3-319-44944-9_10
https://doi.org/10.1007/978-3-319-44944-9_10