Evolution of a local boundary detector for natural images via genetic programming and texture cues

Ilan Kadar; Ohad Ben-Shahar; Moshe Sipper

doi:10.1145/1569901.1570218

Evolution of a local boundary detector for natural images via genetic programming and texture cues

Ilan Kadar, Ohad Ben-Shahar, Moshe Sipper

Department of Computer Science

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

18 Scopus citations

Abstract

Boundary detection constitutes a crucial step in many computer vision tasks. We present a learning approach for automatically constructing high-performance local boundary detectors for natural images via genetic programming (GP). Our GP system is unique in that it combines filter kernels that were inspired by models of processing in the early stages of the primate visual system, but makes no assumptions about what constitutes a boundary, thus avoiding the need to make ad hoc intuitive definitions. By testing our evolved boundary detectors on a highly challenging benchmark set of natural images with associated human-marked boundaries, we show performance that outperforms most existing approaches.

Original language	English
Title of host publication	Proceedings of the 11th Annual Genetic and Evolutionary Computation Conference, GECCO-2009
Pages	1887-1888
Number of pages	2
DOIs	https://doi.org/10.1145/1569901.1570218
State	Published - 31 Dec 2009
Event	11th Annual Genetic and Evolutionary Computation Conference, GECCO-2009 - Montreal, QC, Canada Duration: 8 Jul 2009 → 12 Jul 2009

Conference

Conference	11th Annual Genetic and Evolutionary Computation Conference, GECCO-2009
Country/Territory	Canada
City	Montreal, QC
Period	8/07/09 → 12/07/09

Keywords

Boundary detection
Computer vision
Evolutionary algorithms
Machine learning

ASJC Scopus subject areas

Computational Theory and Mathematics
Theoretical Computer Science

Access to Document

10.1145/1569901.1570218

Cite this

@inproceedings{485b0a4e7a5e40c0a2ea6a248f32b5b6,

title = "Evolution of a local boundary detector for natural images via genetic programming and texture cues",

abstract = "Boundary detection constitutes a crucial step in many computer vision tasks. We present a learning approach for automatically constructing high-performance local boundary detectors for natural images via genetic programming (GP). Our GP system is unique in that it combines filter kernels that were inspired by models of processing in the early stages of the primate visual system, but makes no assumptions about what constitutes a boundary, thus avoiding the need to make ad hoc intuitive definitions. By testing our evolved boundary detectors on a highly challenging benchmark set of natural images with associated human-marked boundaries, we show performance that outperforms most existing approaches.",

keywords = "Boundary detection, Computer vision, Evolutionary algorithms, Machine learning",

author = "Ilan Kadar and Ohad Ben-Shahar and Moshe Sipper",

year = "2009",

month = dec,

day = "31",

doi = "10.1145/1569901.1570218",

language = "English",

isbn = "9781605583259",

pages = "1887--1888",

booktitle = "Proceedings of the 11th Annual Genetic and Evolutionary Computation Conference, GECCO-2009",

note = "11th Annual Genetic and Evolutionary Computation Conference, GECCO-2009 ; Conference date: 08-07-2009 Through 12-07-2009",

}

Kadar, I, Ben-Shahar, O & Sipper, M 2009, Evolution of a local boundary detector for natural images via genetic programming and texture cues. in Proceedings of the 11th Annual Genetic and Evolutionary Computation Conference, GECCO-2009. pp. 1887-1888, 11th Annual Genetic and Evolutionary Computation Conference, GECCO-2009, Montreal, QC, Canada, 8/07/09. https://doi.org/10.1145/1569901.1570218

TY - GEN

T1 - Evolution of a local boundary detector for natural images via genetic programming and texture cues

AU - Kadar, Ilan

AU - Ben-Shahar, Ohad

AU - Sipper, Moshe

PY - 2009/12/31

Y1 - 2009/12/31

N2 - Boundary detection constitutes a crucial step in many computer vision tasks. We present a learning approach for automatically constructing high-performance local boundary detectors for natural images via genetic programming (GP). Our GP system is unique in that it combines filter kernels that were inspired by models of processing in the early stages of the primate visual system, but makes no assumptions about what constitutes a boundary, thus avoiding the need to make ad hoc intuitive definitions. By testing our evolved boundary detectors on a highly challenging benchmark set of natural images with associated human-marked boundaries, we show performance that outperforms most existing approaches.

AB - Boundary detection constitutes a crucial step in many computer vision tasks. We present a learning approach for automatically constructing high-performance local boundary detectors for natural images via genetic programming (GP). Our GP system is unique in that it combines filter kernels that were inspired by models of processing in the early stages of the primate visual system, but makes no assumptions about what constitutes a boundary, thus avoiding the need to make ad hoc intuitive definitions. By testing our evolved boundary detectors on a highly challenging benchmark set of natural images with associated human-marked boundaries, we show performance that outperforms most existing approaches.

KW - Boundary detection

KW - Computer vision

KW - Evolutionary algorithms

KW - Machine learning

UR - http://www.scopus.com/inward/record.url?scp=72749122545&partnerID=8YFLogxK

U2 - 10.1145/1569901.1570218

DO - 10.1145/1569901.1570218

M3 - Conference contribution

AN - SCOPUS:72749122545

SN - 9781605583259

SP - 1887

EP - 1888

BT - Proceedings of the 11th Annual Genetic and Evolutionary Computation Conference, GECCO-2009

T2 - 11th Annual Genetic and Evolutionary Computation Conference, GECCO-2009

Y2 - 8 July 2009 through 12 July 2009

ER -

Evolution of a local boundary detector for natural images via genetic programming and texture cues

Abstract

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this