Special Issue "Soft Computing for Edge Detection"

A special issue of Journal of Imaging (ISSN 2313-433X).

Deadline for manuscript submissions: closed (31 May 2019).

Special Issue Editor

Dr. Carlos Lopez-Molina
E-Mail Website
Guest Editor
Dpto. Estadistica, Informatica y Matematicas, Universidad Publica de Navarra, Pamplona, Spain
Interests: soft computing; fuzzy set theory; image processing; edge detection

Special Issue Information

Dear Colleagues,

Soft computing and image processing have been long associated, especially since the golden age of image processing in 1980s. In the past years, there has been a continuous production of research efforts, which have been mainly characterized as the application of techniques from soft computing to problems in image processing. However, that is not the only possible case, since other authors have elaborated on fuzzy models for image representation, or even on the fuzzy reformulation of already-existing problems in image processing.

The connection between soft computing and image processing is not coincidental, and has a long history. Image processing has historically (although not uniquely) been treated as a signal processing problem, which was subsequently followed by some decisions regarding the presence, absence or measurement of visible artefacts. This schema is very similar to analogical system control, which is the field in which Prof. Zadeh excelled before presenting fuzzy sets in 1965. In fact, it can be said that Zadeh's early works on fuzzy sets were influenced by the need for modelling signal-based information for automated control and decision making. Hence, it is natural that soft computing is used to model the appearance of visual artefacts in image processing.

The coalescence of soft computing and image processing has been embodied in very different paradigms. One initial body of proposals includes the application of soft computing techniques to solve problems stated in terms of standard image processing. From the application of fuzzy sets to the modelling of areas, to the use of fuzzy-rule-based systems, the past years have seen many fuzzy-related techniques applied to the solution of image processing problems. A secondary body of research efforts is due to the reformulation of the basics in image processing in different terms, generally influenced by concepts of granularity, uncertainty modelling or tolerance to imprecision. Finally, a third group of researchers took advantage of the vast developments in mathematics due to fuzzy set theory, by applying those developments to specific tasks in image processing. Remarkable works in any of the three paradigms have been presented and continue to be presented.

One task that has been remarkably tackled from the perspective of soft computing is edge (or boundary) detection. This seems natural for diverse reasons. Edge detection is one of the fields in image processing in which definitions are more imprecise, to the point that there is arguably no definition for the task. Also, the evaluation of edge detection procedures is heavily based on the comparison of edge images to human-labelled edge images, which induces heavy quotas of uncertainty, ambiguity or contradiction to the task. Finally, the fact that edges are materialized as one-pixel-width lines on a discrete universe imposes the need to consider the tolerance for imprecision in terms of pixel- or region-wise information; sticking to the factual numerical information in an image, avoiding considering factors such as noise, shadows and image imperfections could never lead to acceptable results.

This Special Issue attempts to capture the state-of-the-art of edge detection, as tackled from the perspective of soft computing. In this regard, it considers different approximations to edge detection, which are rooted in the mathematical grounds, specific techniques or philosophical foundations of soft computing. This Special Issue is open to considering any approach which, at any stage of an image processing pipeline, attempts to improve the result of an edge detection procedure. It is also open to applications of soft computing procedures that, if not conducent to edge detection themselves, play a clear role in the evolution of the field,examples being edge image evaluation/comparison or edge image fusion.

Dr. Carlos Lopez-Molina
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All papers will be peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Journal of Imaging is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • Edge/boundary detection
  • Edge quality evaluation
  • Image differentiation
  • Edge feature fusion
  • Edge feature binarization

Published Papers (3 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

Article
Shape Similarity Measurement for Known-Object Localization: A New Normalized Assessment
J. Imaging 2019, 5(10), 77; https://0-doi-org.brum.beds.ac.uk/10.3390/jimaging5100077 - 23 Sep 2019
Cited by 2 | Viewed by 2560
Abstract
This paper presents a new, normalized measure for assessing a contour-based object pose. Regarding binary images, the algorithm enables supervised assessment of known-object recognition and localization. A performance measure is computed to quantify differences between a reference edge map and a candidate image. [...] Read more.
This paper presents a new, normalized measure for assessing a contour-based object pose. Regarding binary images, the algorithm enables supervised assessment of known-object recognition and localization. A performance measure is computed to quantify differences between a reference edge map and a candidate image. Normalization is appropriate for interpreting the result of the pose assessment. Furthermore, the new measure is well motivated by highlighting the limitations of existing metrics to the main shape variations (translation, rotation, and scaling), by showing how the proposed measure is more robust to them. Indeed, this measure can determine to what extent an object shape differs from a desired position. In comparison with 6 other approaches, experiments performed on real images at different sizes/scales demonstrate the suitability of the new method for object-pose or shape-matching estimation. Full article
(This article belongs to the Special Issue Soft Computing for Edge Detection)
Show Figures

Figure 1

Article
General Type-2 Fuzzy Sugeno Integral for Edge Detection
J. Imaging 2019, 5(8), 71; https://0-doi-org.brum.beds.ac.uk/10.3390/jimaging5080071 - 16 Aug 2019
Cited by 9 | Viewed by 2825
Abstract
A type-2 fuzzy edge detection method is presented in this paper. The general process consists of first obtaining the image gradients in the four directions—horizontal, vertical, and the two diagonals—and this technique is known as the morphological gradient. After that, the general type-2 [...] Read more.
A type-2 fuzzy edge detection method is presented in this paper. The general process consists of first obtaining the image gradients in the four directions—horizontal, vertical, and the two diagonals—and this technique is known as the morphological gradient. After that, the general type-2 fuzzy Sugeno integral (GT2 FSI) is used to integrate the four image gradients. In this second step, the GT2 FSI establishes criteria to determine at which level the obtained image gradient belongs to an edge during the process; this is calculated assigning different general type-2 fuzzy densities, and these fuzzy gradients are aggregated using the meet and join operators. The gradient integration using the GT2 FSI provides a methodology for achieving more robust edge detection, even more if we are working with blurry images. The experimental evaluations are performed on synthetic and real images, and the accuracy is quantified using Pratt’s Figure of Merit. The results values demonstrate that the proposed edge detection method outperforms other existing algorithms. Full article
(This article belongs to the Special Issue Soft Computing for Edge Detection)
Show Figures

Figure 1

Article
Superpixel Segmentation Based on Anisotropic Edge Strength
J. Imaging 2019, 5(6), 57; https://0-doi-org.brum.beds.ac.uk/10.3390/jimaging5060057 - 05 Jun 2019
Cited by 4 | Viewed by 3416
Abstract
Superpixel segmentation can benefit from the use of an appropriate method to measure edge strength. In this paper, we present such a method based on the first derivative of anisotropic Gaussian kernels. The kernels can capture the position, direction, prominence, and scale of [...] Read more.
Superpixel segmentation can benefit from the use of an appropriate method to measure edge strength. In this paper, we present such a method based on the first derivative of anisotropic Gaussian kernels. The kernels can capture the position, direction, prominence, and scale of the edge to be detected. We incorporate the anisotropic edge strength into the distance measure between neighboring superpixels, thereby improving the performance of an existing graph-based superpixel segmentation method. Experimental results validate the superiority of our method in generating superpixels over the competing methods. It is also illustrated that the proposed superpixel segmentation method can facilitate subsequent saliency detection. Full article
(This article belongs to the Special Issue Soft Computing for Edge Detection)
Show Figures

Figure 1

Back to TopTop