Combining efficient hand-crafted features with learned filters for fast and accurate corneal nerve fibre centreline detection

TY - GEN

T1 - Combining efficient hand-crafted features with learned filters for fast and accurate corneal nerve fibre centreline detection

AU - Annunziata, Roberto

AU - Kheirkhah, Ahmad

AU - Hamrah, Pedram

AU - Trucco, Emanuele

N1 - Conference code: 37

PY - 2015/11/4

Y1 - 2015/11/4

N2 - We propose a new approach to corneal nerve fibre centreline detection for in vivo confocal microscopy images. Relying on a combination of efficient hand-crafted features and learned filters, our method offers an excellent compromise between accuracy and running time. Unlike previous solutions using sparse coding to learn small filter banks, we employ K-means to efficiently learn the high amount of filters needed to cope with the multiple challenges involved, e.g., low contrast and resolution, non-uniform illumination, tortuosity and confounding non-target structures. The use of K-means for dictionary learning allows us to learn banks of 100 filters in less than 30 seconds compared to several days needed when using sparse coding. Experimental results using a dataset including 100 images show that our approach outperforms significantly state-of-the-art methods in terms of precision-recall curves.

AB - We propose a new approach to corneal nerve fibre centreline detection for in vivo confocal microscopy images. Relying on a combination of efficient hand-crafted features and learned filters, our method offers an excellent compromise between accuracy and running time. Unlike previous solutions using sparse coding to learn small filter banks, we employ K-means to efficiently learn the high amount of filters needed to cope with the multiple challenges involved, e.g., low contrast and resolution, non-uniform illumination, tortuosity and confounding non-target structures. The use of K-means for dictionary learning allows us to learn banks of 100 filters in less than 30 seconds compared to several days needed when using sparse coding. Experimental results using a dataset including 100 images show that our approach outperforms significantly state-of-the-art methods in terms of precision-recall curves.

UR - https://www.scopus.com/pages/publications/84953257114

U2 - 10.1109/EMBC.2015.7319675

DO - 10.1109/EMBC.2015.7319675

M3 - Conference contribution

C2 - 26737575

AN - SCOPUS:84953257114

SN - 9781424492718

SP - 5655

EP - 5658

BT - 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

PB - Institute of Electrical and Electronics Engineers

T2 - 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2015

Y2 - 25 August 2015 through 29 August 2015

ER -