From line segments to more organized gestalts

Boshra RAJAEI; Rafael GROMPONE VON GIOI; Jean-Michel MOREL

doi:10.1109/SSIAI.2016.7459194

From line segments to more organized gestalts

Boshra RAJAEI
, Rafael GROMPONE VON GIOI
, Jean-Michel MOREL

Research output: Book Chapters | Papers in Conference Proceedings › Conference paper (refereed) › Research › peer-review

7 Citations (Scopus)

Abstract

In this paper, we reconsider the early computer vision bottom-up program, according to which higher level features (geometric structures) in an image could be built up recursively from elementary features by simple grouping principles coming from Gestalt theory. Taking advantage of the (recent) advances in reliable line segment detectors, we propose three feature detectors that constitute one step up in this bottom up pyramid. For any digital image, our unsupervised algorithm computes three classic Gestalts from the set of predetected line segments: good continuations, nonlocal alignments, and bars. The methodology is based on a common stochastic a contrario model yielding three simple detection formulas, characterized by their number of false alarms. This detection algorithm is illustrated on several digital images.

Original language	English
Title of host publication	2016 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2016, Proceedings
Publisher	IEEE
Pages	137-140
Number of pages	4
ISBN (Electronic)	9781467399197
ISBN (Print)	9781467399180
DOIs	https://doi.org/10.1109/SSIAI.2016.7459194
Publication status	Published - 2016
Externally published	Yes
Event	2016 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2016, Proceedings - Santa Fe, United States Duration: 6 Mar 2016 → 8 Mar 2016

Symposium

Symposium	2016 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2016, Proceedings
Country/Territory	United States
City	Santa Fe
Period	6/03/16 → 8/03/16

Funding

Work partly founded by the European Research Council (advanced grant Twelve Labours no 246961).

Keywords

a contrario detection
Gestalt detector
line segment detector (LSD)
non-accidentalness principle
number of false alarms (NFA)

Access to Document

10.1109/SSIAI.2016.7459194

Cite this

@inproceedings{0e8635e773ba49d1ac276dfac2c87e3f,

title = "From line segments to more organized gestalts",

abstract = "In this paper, we reconsider the early computer vision bottom-up program, according to which higher level features (geometric structures) in an image could be built up recursively from elementary features by simple grouping principles coming from Gestalt theory. Taking advantage of the (recent) advances in reliable line segment detectors, we propose three feature detectors that constitute one step up in this bottom up pyramid. For any digital image, our unsupervised algorithm computes three classic Gestalts from the set of predetected line segments: good continuations, nonlocal alignments, and bars. The methodology is based on a common stochastic a contrario model yielding three simple detection formulas, characterized by their number of false alarms. This detection algorithm is illustrated on several digital images.",

keywords = "a contrario detection, Gestalt detector, line segment detector (LSD), non-accidentalness principle, number of false alarms (NFA)",

author = "Boshra RAJAEI and \{GROMPONE VON GIOI\}, Rafael and Jean-Michel MOREL",

year = "2016",

doi = "10.1109/SSIAI.2016.7459194",

language = "English",

isbn = "9781467399180",

pages = "137--140",

booktitle = "2016 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2016, Proceedings",

publisher = "IEEE",

note = "2016 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2016, Proceedings ; Conference date: 06-03-2016 Through 08-03-2016",

}

RAJAEI, B, GROMPONE VON GIOI, R & MOREL, J-M 2016, From line segments to more organized gestalts. in 2016 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2016, Proceedings., 7459194, IEEE, pp. 137-140, 2016 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2016, Proceedings, Santa Fe, New Mexico, United States, 6/03/16. https://doi.org/10.1109/SSIAI.2016.7459194

TY - GEN

T1 - From line segments to more organized gestalts

AU - RAJAEI, Boshra

AU - GROMPONE VON GIOI, Rafael

AU - MOREL, Jean-Michel

PY - 2016

Y1 - 2016

N2 - In this paper, we reconsider the early computer vision bottom-up program, according to which higher level features (geometric structures) in an image could be built up recursively from elementary features by simple grouping principles coming from Gestalt theory. Taking advantage of the (recent) advances in reliable line segment detectors, we propose three feature detectors that constitute one step up in this bottom up pyramid. For any digital image, our unsupervised algorithm computes three classic Gestalts from the set of predetected line segments: good continuations, nonlocal alignments, and bars. The methodology is based on a common stochastic a contrario model yielding three simple detection formulas, characterized by their number of false alarms. This detection algorithm is illustrated on several digital images.

AB - In this paper, we reconsider the early computer vision bottom-up program, according to which higher level features (geometric structures) in an image could be built up recursively from elementary features by simple grouping principles coming from Gestalt theory. Taking advantage of the (recent) advances in reliable line segment detectors, we propose three feature detectors that constitute one step up in this bottom up pyramid. For any digital image, our unsupervised algorithm computes three classic Gestalts from the set of predetected line segments: good continuations, nonlocal alignments, and bars. The methodology is based on a common stochastic a contrario model yielding three simple detection formulas, characterized by their number of false alarms. This detection algorithm is illustrated on several digital images.

KW - a contrario detection

KW - Gestalt detector

KW - line segment detector (LSD)

KW - non-accidentalness principle

KW - number of false alarms (NFA)

UR - https://www.scopus.com/pages/publications/84971273080

U2 - 10.1109/SSIAI.2016.7459194

DO - 10.1109/SSIAI.2016.7459194

M3 - Conference paper (refereed)

AN - SCOPUS:84971273080

SN - 9781467399180

SP - 137

EP - 140

BT - 2016 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2016, Proceedings

PB - IEEE

T2 - 2016 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2016, Proceedings

Y2 - 6 March 2016 through 8 March 2016

ER -

From line segments to more organized gestalts

Abstract

Symposium

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this