Publication

Robust Inhibition-Augmented Operator for Delineation of Curvilinear Structures

Strisciuglio, N., Azzopardi, G. & Petkov, N., Dec-2019, In : Ieee transactions on image processing. 28, 12, p. 5852-5866 15 p.

Research output: Contribution to journalArticleAcademicpeer-review

APA

Strisciuglio, N., Azzopardi, G., & Petkov, N. (2019). Robust Inhibition-Augmented Operator for Delineation of Curvilinear Structures. Ieee transactions on image processing, 28(12), 5852-5866. https://doi.org/10.1109/TIP.2019.2922096

Author

Strisciuglio, Nicola ; Azzopardi, George ; Petkov, Nicolai. / Robust Inhibition-Augmented Operator for Delineation of Curvilinear Structures. In: Ieee transactions on image processing. 2019 ; Vol. 28, No. 12. pp. 5852-5866.

Harvard

Strisciuglio, N, Azzopardi, G & Petkov, N 2019, 'Robust Inhibition-Augmented Operator for Delineation of Curvilinear Structures', Ieee transactions on image processing, vol. 28, no. 12, pp. 5852-5866. https://doi.org/10.1109/TIP.2019.2922096

Standard

Robust Inhibition-Augmented Operator for Delineation of Curvilinear Structures. / Strisciuglio, Nicola; Azzopardi, George; Petkov, Nicolai.

In: Ieee transactions on image processing, Vol. 28, No. 12, 12.2019, p. 5852-5866.

Research output: Contribution to journalArticleAcademicpeer-review

Vancouver

Strisciuglio N, Azzopardi G, Petkov N. Robust Inhibition-Augmented Operator for Delineation of Curvilinear Structures. Ieee transactions on image processing. 2019 Dec;28(12):5852-5866. https://doi.org/10.1109/TIP.2019.2922096


BibTeX

@article{7bef7bf56c36407683e347bd61e63910,
title = "Robust Inhibition-Augmented Operator for Delineation of Curvilinear Structures",
abstract = "Delineation of curvilinear structures in images is an important basic step of several image processing applications, such as segmentation of roads or rivers in aerial images, vessels or staining membranes in medical images, and cracks in pavements and roads, among others. Existing methods suffer from insufficient robustness to noise. In this paper, we propose a novel operator for the detection of curvilinear structures in images, which we demonstrate to be robust to various types of noise and effective in several applications. We call it RUSTICO, which stands for RobUST Inhibition-augmented Curvilinear Operator. It is inspired by the push-pull inhibition in visual cortex and takes as input the responses of two trainable B-COSFIRE filters of opposite polarity. The output of RUSTICO consists of a magnitude map and an orientation map. We carried out experiments on a data set of synthetic stimuli with noise drawn from different distributions, as well as on several benchmark data sets of retinal fundus images, crack pavements, and aerial images and a new data set of rose bushes used for automatic gardening. We evaluated the performance of RUSTICO by a metric that considers the structural properties of line networks (connectivity, area, and length) and demonstrated that RUSTICO outperforms many existing methods with high statistical significance. RUSTICO exhibits high robustness to noise and texture.",
keywords = "Curvilinear structures, delineation, non-linear filtering, noise inhibition, orientation map, RETINAL VESSEL SEGMENTATION, TRAINABLE COSFIRE FILTERS, BLOOD-VESSELS, ORIENTATION SELECTIVITY, MATCHED-FILTER, IMAGES, MODEL, CLASSIFIERS, RESPONSES, NETWORKS",
author = "Nicola Strisciuglio and George Azzopardi and Nicolai Petkov",
year = "2019",
month = "12",
doi = "10.1109/TIP.2019.2922096",
language = "English",
volume = "28",
pages = "5852--5866",
journal = "Ieee transactions on image processing",
issn = "1057-7149",
publisher = "IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC",
number = "12",

}

RIS

TY - JOUR

T1 - Robust Inhibition-Augmented Operator for Delineation of Curvilinear Structures

AU - Strisciuglio, Nicola

AU - Azzopardi, George

AU - Petkov, Nicolai

PY - 2019/12

Y1 - 2019/12

N2 - Delineation of curvilinear structures in images is an important basic step of several image processing applications, such as segmentation of roads or rivers in aerial images, vessels or staining membranes in medical images, and cracks in pavements and roads, among others. Existing methods suffer from insufficient robustness to noise. In this paper, we propose a novel operator for the detection of curvilinear structures in images, which we demonstrate to be robust to various types of noise and effective in several applications. We call it RUSTICO, which stands for RobUST Inhibition-augmented Curvilinear Operator. It is inspired by the push-pull inhibition in visual cortex and takes as input the responses of two trainable B-COSFIRE filters of opposite polarity. The output of RUSTICO consists of a magnitude map and an orientation map. We carried out experiments on a data set of synthetic stimuli with noise drawn from different distributions, as well as on several benchmark data sets of retinal fundus images, crack pavements, and aerial images and a new data set of rose bushes used for automatic gardening. We evaluated the performance of RUSTICO by a metric that considers the structural properties of line networks (connectivity, area, and length) and demonstrated that RUSTICO outperforms many existing methods with high statistical significance. RUSTICO exhibits high robustness to noise and texture.

AB - Delineation of curvilinear structures in images is an important basic step of several image processing applications, such as segmentation of roads or rivers in aerial images, vessels or staining membranes in medical images, and cracks in pavements and roads, among others. Existing methods suffer from insufficient robustness to noise. In this paper, we propose a novel operator for the detection of curvilinear structures in images, which we demonstrate to be robust to various types of noise and effective in several applications. We call it RUSTICO, which stands for RobUST Inhibition-augmented Curvilinear Operator. It is inspired by the push-pull inhibition in visual cortex and takes as input the responses of two trainable B-COSFIRE filters of opposite polarity. The output of RUSTICO consists of a magnitude map and an orientation map. We carried out experiments on a data set of synthetic stimuli with noise drawn from different distributions, as well as on several benchmark data sets of retinal fundus images, crack pavements, and aerial images and a new data set of rose bushes used for automatic gardening. We evaluated the performance of RUSTICO by a metric that considers the structural properties of line networks (connectivity, area, and length) and demonstrated that RUSTICO outperforms many existing methods with high statistical significance. RUSTICO exhibits high robustness to noise and texture.

KW - Curvilinear structures

KW - delineation

KW - non-linear filtering

KW - noise inhibition

KW - orientation map

KW - RETINAL VESSEL SEGMENTATION

KW - TRAINABLE COSFIRE FILTERS

KW - BLOOD-VESSELS

KW - ORIENTATION SELECTIVITY

KW - MATCHED-FILTER

KW - IMAGES

KW - MODEL

KW - CLASSIFIERS

KW - RESPONSES

KW - NETWORKS

U2 - 10.1109/TIP.2019.2922096

DO - 10.1109/TIP.2019.2922096

M3 - Article

VL - 28

SP - 5852

EP - 5866

JO - Ieee transactions on image processing

JF - Ieee transactions on image processing

SN - 1057-7149

IS - 12

ER -

ID: 83661125