Detection of curved lines with B-COSFIRE filters: A case study on crack delineation

Nicola Strisciuglio; George Azzopardi; Nicolai Petkov

doi:10.1007/978-3-319-64689-3_9

Detection of curved lines with B-COSFIRE filters: A case study on crack delineation

Nicola Strisciuglio^*
, George Azzopardi
, Nicolai Petkov

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

20 Citations (Scopus)

Abstract

The detection of curvilinear structures is an important step for various computer vision applications, ranging from medical image analysis for segmentation of blood vessels, to remote sensing for the identification of roads and rivers, and to biometrics and robotics, among others. This is a nontrivial task especially for the detection of thin or incomplete curvilinear structures surrounded with noise. We propose a general purpose curvilinear structure detector that uses the brain-inspired trainable B-COSFIRE filters. It consists of four main steps, namely nonlinear filtering with B-COSFIRE, thinning with non-maximum suppression, hysteresis thresholding and morphological closing. We demonstrate its effectiveness on a data set of noisy images with cracked pavements, where we achieve state-of-the-art results (F-measure = 0.865 ). The proposed method can be employed in any computer vision methodology that requires the delineation of curvilinear and elongated structures.

Original language	English
Title of host publication	Computer Analysis of Images and Patterns
Subtitle of host publication	17th International Conference, CAIP 2017, Ystad, Sweden, August 22-24, 2017, Proceedings, Part I
Editors	Michael Felsberg, Anders Heyden, Norbert Krüger
Place of Publication	Cham
Publisher	Springer
Pages	108-120
Number of pages	13
ISBN (Electronic)	978-3-319-64689-3
ISBN (Print)	978-3-319-64688-6
DOIs	https://doi.org/10.1007/978-3-319-64689-3_9
Publication status	Published - 1 Jan 2017
Externally published	Yes
Event	17th International Conference on Computer Analysis of Images and Patterns, CAIP 2017 - Ystad, Sweden Duration: 22 Aug 2017 → 24 Aug 2017 Conference number: 17

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer
Volume	10424
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	17th International Conference on Computer Analysis of Images and Patterns, CAIP 2017
Abbreviated title	CAIP
Country/Territory	Sweden
City	Ystad
Period	22/08/17 → 24/08/17

Keywords

COSFIRE
Crack delineation
Curved lines
Line detection
Non-linear filtering

Access to Document

10.1007/978-3-319-64689-3_9

Cite this

Strisciuglio, N., Azzopardi, G., & Petkov, N. (2017). Detection of curved lines with B-COSFIRE filters: A case study on crack delineation. In M. Felsberg, A. Heyden, & N. Krüger (Eds.), Computer Analysis of Images and Patterns: 17th International Conference, CAIP 2017, Ystad, Sweden, August 22-24, 2017, Proceedings, Part I (pp. 108-120). (Lecture Notes in Computer Science; Vol. 10424). Springer. https://doi.org/10.1007/978-3-319-64689-3_9

Strisciuglio, Nicola ; Azzopardi, George ; Petkov, Nicolai. / Detection of curved lines with B-COSFIRE filters : A case study on crack delineation. Computer Analysis of Images and Patterns: 17th International Conference, CAIP 2017, Ystad, Sweden, August 22-24, 2017, Proceedings, Part I. editor / Michael Felsberg ; Anders Heyden ; Norbert Krüger. Cham : Springer, 2017. pp. 108-120 (Lecture Notes in Computer Science).

@inproceedings{f91db564482f4a6e8c3c6163bcfe4593,

title = "Detection of curved lines with B-COSFIRE filters: A case study on crack delineation",

abstract = "The detection of curvilinear structures is an important step for various computer vision applications, ranging from medical image analysis for segmentation of blood vessels, to remote sensing for the identification of roads and rivers, and to biometrics and robotics, among others. This is a nontrivial task especially for the detection of thin or incomplete curvilinear structures surrounded with noise. We propose a general purpose curvilinear structure detector that uses the brain-inspired trainable B-COSFIRE filters. It consists of four main steps, namely nonlinear filtering with B-COSFIRE, thinning with non-maximum suppression, hysteresis thresholding and morphological closing. We demonstrate its effectiveness on a data set of noisy images with cracked pavements, where we achieve state-of-the-art results (F-measure = 0.865 ). The proposed method can be employed in any computer vision methodology that requires the delineation of curvilinear and elongated structures.",

keywords = "COSFIRE, Crack delineation, Curved lines, Line detection, Non-linear filtering",

author = "Nicola Strisciuglio and George Azzopardi and Nicolai Petkov",

year = "2017",

month = jan,

day = "1",

doi = "10.1007/978-3-319-64689-3\_9",

language = "English",

isbn = "978-3-319-64688-6",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "108--120",

editor = "Michael Felsberg and Anders Heyden and Norbert Kr{\"u}ger",

booktitle = "Computer Analysis of Images and Patterns",

address = "Germany",

note = "17th International Conference on Computer Analysis of Images and Patterns, CAIP 2017, CAIP ; Conference date: 22-08-2017 Through 24-08-2017",

}

Strisciuglio, N, Azzopardi, G & Petkov, N 2017, Detection of curved lines with B-COSFIRE filters: A case study on crack delineation. in M Felsberg, A Heyden & N Krüger (eds), Computer Analysis of Images and Patterns: 17th International Conference, CAIP 2017, Ystad, Sweden, August 22-24, 2017, Proceedings, Part I. Lecture Notes in Computer Science, vol. 10424, Springer, Cham, pp. 108-120, 17th International Conference on Computer Analysis of Images and Patterns, CAIP 2017, Ystad, Sweden, 22/08/17. https://doi.org/10.1007/978-3-319-64689-3_9

Detection of curved lines with B-COSFIRE filters: A case study on crack delineation. / Strisciuglio, Nicola; Azzopardi, George; Petkov, Nicolai.
Computer Analysis of Images and Patterns: 17th International Conference, CAIP 2017, Ystad, Sweden, August 22-24, 2017, Proceedings, Part I. ed. / Michael Felsberg; Anders Heyden; Norbert Krüger. Cham: Springer, 2017. p. 108-120 (Lecture Notes in Computer Science; Vol. 10424).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Detection of curved lines with B-COSFIRE filters

T2 - 17th International Conference on Computer Analysis of Images and Patterns, CAIP 2017

AU - Strisciuglio, Nicola

AU - Azzopardi, George

AU - Petkov, Nicolai

N1 - Conference code: 17

PY - 2017/1/1

Y1 - 2017/1/1

N2 - The detection of curvilinear structures is an important step for various computer vision applications, ranging from medical image analysis for segmentation of blood vessels, to remote sensing for the identification of roads and rivers, and to biometrics and robotics, among others. This is a nontrivial task especially for the detection of thin or incomplete curvilinear structures surrounded with noise. We propose a general purpose curvilinear structure detector that uses the brain-inspired trainable B-COSFIRE filters. It consists of four main steps, namely nonlinear filtering with B-COSFIRE, thinning with non-maximum suppression, hysteresis thresholding and morphological closing. We demonstrate its effectiveness on a data set of noisy images with cracked pavements, where we achieve state-of-the-art results (F-measure = 0.865 ). The proposed method can be employed in any computer vision methodology that requires the delineation of curvilinear and elongated structures.

AB - The detection of curvilinear structures is an important step for various computer vision applications, ranging from medical image analysis for segmentation of blood vessels, to remote sensing for the identification of roads and rivers, and to biometrics and robotics, among others. This is a nontrivial task especially for the detection of thin or incomplete curvilinear structures surrounded with noise. We propose a general purpose curvilinear structure detector that uses the brain-inspired trainable B-COSFIRE filters. It consists of four main steps, namely nonlinear filtering with B-COSFIRE, thinning with non-maximum suppression, hysteresis thresholding and morphological closing. We demonstrate its effectiveness on a data set of noisy images with cracked pavements, where we achieve state-of-the-art results (F-measure = 0.865 ). The proposed method can be employed in any computer vision methodology that requires the delineation of curvilinear and elongated structures.

KW - COSFIRE

KW - Crack delineation

KW - Curved lines

KW - Line detection

KW - Non-linear filtering

UR - https://www.scopus.com/pages/publications/85028504152

U2 - 10.1007/978-3-319-64689-3_9

DO - 10.1007/978-3-319-64689-3_9

M3 - Conference contribution

AN - SCOPUS:85028504152

SN - 978-3-319-64688-6

T3 - Lecture Notes in Computer Science

SP - 108

EP - 120

BT - Computer Analysis of Images and Patterns

A2 - Felsberg, Michael

A2 - Heyden, Anders

A2 - Krüger, Norbert

PB - Springer

CY - Cham

Y2 - 22 August 2017 through 24 August 2017

ER -

Strisciuglio N, Azzopardi G, Petkov N. Detection of curved lines with B-COSFIRE filters: A case study on crack delineation. In Felsberg M, Heyden A, Krüger N, editors, Computer Analysis of Images and Patterns: 17th International Conference, CAIP 2017, Ystad, Sweden, August 22-24, 2017, Proceedings, Part I. Cham: Springer. 2017. p. 108-120. (Lecture Notes in Computer Science). doi: 10.1007/978-3-319-64689-3_9

Detection of curved lines with B-COSFIRE filters: A case study on crack delineation

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this