Joint Contours, Corner and T-Junction Detection: An Approach Inspired by the Mammal Visual System

Buades, Antoni; Gioi, Rafael Grompone von; Navarro, José Bonet

doi:10.1007/s10851-017-0763-z

Cited by 8 publications

(16 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We implement the method proposed by Buades, Grompone and Navarro [2]. The aim of [2] is to jointly identify contours, line segments, corners and T-junctions.…”

Section: Introductionmentioning

confidence: 99%

“…The aim of [2] is to jointly identify contours, line segments, corners and T-junctions. It is inspired by the first stages of the mammal visual system.…”

Section: Introductionmentioning

confidence: 99%

“…The work in [2] is also motivated by a contrario validation, introduced into digital imaging by Desolneux, Moisan and Morel [6]. The authors defined those geometrical configurations that cannot be observed by chance as meaningful.…”

Section: Introductionmentioning

confidence: 99%

“…The method in [2] is capable of dealing efficiently with line segment and contour detection, as well as corner and T-junction identification. Since these features are complementary, a unified procedure should identify all at once.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Contours, Corners and T-Junctions Detection Algorithm

Buades¹,

Gioi²,

Navarro³

2018

Image Processing on Line

Self Cite

View full text Add to dashboard Cite

This article describes the implementation of the method proposed by Buades, Grompone and Navarro in 2017 for the detection of line segments, contours, corners and T-junctions. The method is inspired by the mammal visual system. The detection of corners and T-junctions plays a role as part of the process in contour detection. An a contrario validation is applied to select the most meaningful contours without the need of fixing any critical parameter. Source CodeThe reviewed source code and documentation for this algorithm are available from the web page of this article 1 . Compilation and usage instruction are included in the README.txt file of the archive.

show abstract

“…We implement the method proposed by Buades, Grompone and Navarro [2]. The aim of [2] is to jointly identify contours, line segments, corners and T-junctions.…”

Section: Introductionmentioning

confidence: 99%

“…The aim of [2] is to jointly identify contours, line segments, corners and T-junctions. It is inspired by the first stages of the mammal visual system.…”

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Contours, Corners and T-Junctions Detection Algorithm

Buades¹,

Gioi²,

Navarro³

2018

Image Processing on Line

Self Cite

View full text Add to dashboard Cite

show abstract

“…Although the HT has proven to be a relevant technique for the detection of multiple shapes and image features (Mukhopadhyay and Chaudhuri, 2014 ), it is worth noting that other methods exist for the joint detection of lines, contours, junctions, and corners. A remarkable alternative is the work presented in Buades et al ( 2017 ) which, although biologically inspired, does not rely on neural networks. For a given image, their proposal computes the response of a pool of oriented filters and groups the result of the filters in a way that enables detecting contours, corners and T-junctions.…”

Section: Introductionmentioning

confidence: 99%

A Spiking Neural Model of HT3D for Corner Detection

Bachiller

Manso

Bustos

2018

Front. Comput. Neurosci.

View full text Add to dashboard Cite

Obtaining good quality image features is of remarkable importance for most computer vision tasks. It has been demonstrated that the first layers of the human visual cortex are devoted to feature detection. The need for these features has made line, segment, and corner detection one of the most studied topics in computer vision. HT3D is a recent variant of the Hough transform for the combined detection of corners and line segments in images. It uses a 3D parameter space that enables the detection of segments instead of whole lines. This space also encloses canonical configurations of image corners, transforming corner detection into a pattern search problem. Spiking neural networks (SNN) have previously been proposed for multiple image processing tasks, including corner and line detection using the Hough transform. Following these ideas, this paper presents and describes in detail a model to implement HT3D as a Spiking Neural Network for corner detection. The results obtained from a thorough testing of its implementation using real images evince the correctness of the Spiking Neural Network HT3D implementation. Such results are comparable to those obtained with the regular HT3D implementation, which are in turn superior to other corner detection algorithms.

show abstract