Special Issue "Fuzzy Logic for Image Processing"

A special issue of Information (ISSN 2078-2489). This special issue belongs to the section "Artificial Intelligence".

Deadline for manuscript submissions: closed (30 June 2017)

Special Issue Editors

Guest Editor
Prof. Dr. Giovanna Castellano

Department of Informatics, University of Bari "Aldo Moro", Bari, Italy
Website | E-Mail
Phone: +39 80 5442456
Interests: image processing; fuzzy logic; pattern recognition; computer vision; fuzzy clustering
Guest Editor
Prof. Dr. Laura Caponetti

Department of Informatics, University of Bari "Aldo Moro", Bari, Italy
Website | E-Mail
Interests: image processing; fuzzy logic; pattern recognition; computer vision; fuzzy clustering

Special Issue Information

Dear Colleagues,

The increasing availability of huge image collections in different application fields, such as medical diagnosis, remote sensing, transmission and encoding, machine/robot vision, video processing, microscopic imaging has pressed the need, in the last few last years, for the development of efficient techniques capable of managing/processing large collection of image data, and which are suitable for analysis, indexing and retrieval of image data.

Classical image processing methods often face great difficulties while dealing with images containing noise and distortions. Under such conditions, fuzzy logic techniques turn out to be effective to address challenging real-world image processing problems. The main objective of this Special Issue is to show the potential of fuzzy techniques in challenging applications involving tasks related to understand, represent, and process digital images.

This Special Issue will focus on the exploration of the fundamental roles, as well as practical impacts of fuzzy techniques, in the field of image processing. Prospective authors are invited to submit previously unpublished works in these areas. Possible topics include (but are not limited to) applications of fuzzy logic in image processing, leading to advanced fuzzy techniques for:

  • Low-medium level image processing: Contrast enhancement, edge detection, noise detection and removal, segmentation, geometric measurement, and clustering of image data
  • High-level image/scene analysis: Pattern recognition and scene description, modeling of image data, object matching, image annotation, and image retrieval
  • Real-world applications, such as medical/biological image segmentation, face recognition, industrial product inspection, automated surveillance, finger print and biometric security systems.

Time Schedule & Deadlines
Abstract Submission: 15 March 2017
Acceptance Notification: 30 March 2017
Manuscript Submissions: 30 June 2017

Prof. Dr. Giovanna Castellano
Prof. Dr. Laura Caponetti
Guest Editors

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. Information is an international peer-reviewed open access quarterly 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 350 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.

Published Papers (4 papers)

View options order results:
result details:
Displaying articles 1-4
Export citation of selected articles as:

Research

Jump to: Review

Open AccessArticle Edge Detection Method Based on General Type-2 Fuzzy Logic Applied to Color Images
Information 2017, 8(3), 104; doi:10.3390/info8030104
Received: 1 July 2017 / Revised: 22 August 2017 / Accepted: 25 August 2017 / Published: 28 August 2017
PDF Full-text (24536 KB) | HTML Full-text | XML Full-text
Abstract
This paper presents a new general type-2 fuzzy logic method for edge detection applied to color format images. The proposed algorithm combines the methodology based on the image gradients and general type-2 fuzzy logic theory to provide a powerful edge detection method. General
[...] Read more.
This paper presents a new general type-2 fuzzy logic method for edge detection applied to color format images. The proposed algorithm combines the methodology based on the image gradients and general type-2 fuzzy logic theory to provide a powerful edge detection method. General type-2 fuzzy inference systems are approximated using the α-planes approach. The edge detection method is tested on a database of color images with the idea of illustrating the advantage of applying the fuzzy edge detection approach on color images against grayscale format images, and also when the images are corrupted by noise. This paper compares the proposed method based on general type-2 fuzzy logic with other edge detection algorithms, such as ones based on type-1 and interval type-2 fuzzy systems. Simulation results show that edge detection based on a general type-2 fuzzy system outperforms the other methods because of its ability to handle the intrinsic uncertainty in this problem. Full article
(This article belongs to the Special Issue Fuzzy Logic for Image Processing)
Figures

Figure 1

Open AccessArticle Fuzzy Color Clustering for Melanoma Diagnosis in Dermoscopy Images
Information 2017, 8(3), 89; doi:10.3390/info8030089
Received: 20 May 2017 / Revised: 21 July 2017 / Accepted: 21 July 2017 / Published: 25 July 2017
PDF Full-text (3194 KB) | HTML Full-text | XML Full-text
Abstract
A fuzzy logic-based color histogram analysis technique is presented for discriminating benign skin lesions from malignant melanomas in dermoscopy images. The approach extends previous research for utilizing a fuzzy set for skin lesion color for a specified class of skin lesions, using alpha-cut
[...] Read more.
A fuzzy logic-based color histogram analysis technique is presented for discriminating benign skin lesions from malignant melanomas in dermoscopy images. The approach extends previous research for utilizing a fuzzy set for skin lesion color for a specified class of skin lesions, using alpha-cut and support set cardinality for quantifying a fuzzy ratio skin lesion color feature. Skin lesion discrimination results are reported for the fuzzy clustering ratio over different regions of the lesion over a data set of 517 dermoscopy images consisting of 175 invasive melanomas and 342 benign lesions. Experimental results show that the fuzzy clustering ratio applied over an eight-connected neighborhood on the outer 25% of the skin lesion with an alpha-cut of 0.08 can recognize 92.6% of melanomas with approximately 13.5% false positive lesions. These results show the critical importance of colors in the lesion periphery. Our fuzzy logic-based description of lesion colors offers relevance to clinical descriptions of malignant melanoma. Full article
(This article belongs to the Special Issue Fuzzy Logic for Image Processing)
Figures

Figure 1

Open AccessArticle Automated Prostate Gland Segmentation Based on an Unsupervised Fuzzy C-Means Clustering Technique Using Multispectral T1w and T2w MR Imaging
Information 2017, 8(2), 49; doi:10.3390/info8020049
Received: 4 February 2017 / Revised: 3 April 2017 / Accepted: 24 April 2017 / Published: 28 April 2017
PDF Full-text (4264 KB) | HTML Full-text | XML Full-text
Abstract
Prostate imaging analysis is difficult in diagnosis, therapy, and staging of prostate cancer. In clinical practice, Magnetic Resonance Imaging (MRI) is increasingly used thanks to its morphologic and functional capabilities. However, manual detection and delineation of prostate gland on multispectral MRI data is
[...] Read more.
Prostate imaging analysis is difficult in diagnosis, therapy, and staging of prostate cancer. In clinical practice, Magnetic Resonance Imaging (MRI) is increasingly used thanks to its morphologic and functional capabilities. However, manual detection and delineation of prostate gland on multispectral MRI data is currently a time-expensive and operator-dependent procedure. Efficient computer-assisted segmentation approaches are not yet able to address these issues, but rather have the potential to do so. In this paper, a novel automatic prostate MR image segmentation method based on the Fuzzy C-Means (FCM) clustering algorithm, which enables multispectral T1-weighted (T1w) and T2-weighted (T2w) MRI anatomical data processing, is proposed. This approach, using an unsupervised Machine Learning technique, helps to segment the prostate gland effectively. A total of 21 patients with suspicion of prostate cancer were enrolled in this study. Volume-based metrics, spatial overlap-based metrics and spatial distance-based metrics were used to quantitatively evaluate the accuracy of the obtained segmentation results with respect to the gold-standard boundaries delineated manually by an expert radiologist. The proposed multispectral segmentation method was compared with the same processing pipeline applied on either T2w or T1w MR images alone. The multispectral approach considerably outperforms the monoparametric ones, achieving an average Dice Similarity Coefficient 90.77 ± 1.75, with respect to 81.90 ± 6.49 and 82.55 ± 4.93 by processing T2w and T1w imaging alone, respectively. Combining T2w and T1w MR image structural information significantly enhances prostate gland segmentation by exploiting the uniform gray appearance of the prostate on T1w MRI. Full article
(This article belongs to the Special Issue Fuzzy Logic for Image Processing)
Figures

Figure 1

Review

Jump to: Research

Open AccessReview Review of Recent Type-2 Fuzzy Image Processing Applications
Information 2017, 8(3), 97; doi:10.3390/info8030097
Received: 30 June 2017 / Revised: 5 August 2017 / Accepted: 8 August 2017 / Published: 10 August 2017
PDF Full-text (2462 KB) | HTML Full-text | XML Full-text
Abstract
This paper presents a literature review of applications using type-2 fuzzy systems in the area of image processing. Over the last years, there has been a significant increase in research on higher-order forms of fuzzy logic; in particular, the use of interval type-2
[...] Read more.
This paper presents a literature review of applications using type-2 fuzzy systems in the area of image processing. Over the last years, there has been a significant increase in research on higher-order forms of fuzzy logic; in particular, the use of interval type-2 fuzzy sets and general type-2 fuzzy sets. The idea of making use of higher orders, or types, of fuzzy logic is to capture and represent uncertainty that is more complex. This paper is focused on image processing systems, which includes image segmentation, image filtering, image classification and edge detection. Various applications are presented where general type-2 fuzzy sets, interval type-2 fuzzy sets, and interval-value fuzzy sets are used; some are compared with the traditional type-1 fuzzy sets and others methodologies that exist in the literature for these areas in image processing. In all accounts, it is shown that type-2 fuzzy sets outperform both traditional image processing techniques as well as techniques using type-1 fuzzy sets, and provide the ability to handle uncertainty when the image is corrupted by noise. Full article
(This article belongs to the Special Issue Fuzzy Logic for Image Processing)
Figures

Figure 1

Planned Papers

The below list represents only planned manuscripts. Some of these manuscripts have not been received by the Editorial Office yet. Papers submitted to MDPI journals are subject to peer-review.

Title: MR Brain Image Segmentation: Comparing Different Clustering Techniques
Authors: Giovanna Castellano, Laura Caponetti and Vito Corsini
Affiliation: Department of Informatics, University of Bari "Aldo Moro", Bari, Italy
Abstract: Magnetic resonance (MR) brain image segmentation is a critical requirement in the diagnosis of neurological diseases since it enables automatic identification of anatomical structures or tissue types in the brain. In this paper we are interested in clustering methods for MR brain image segmentation. A comparison is made among different fuzzy clustering algorithms. Comparison is made not only qualitatively, through visual inspection of segmented images, but also quantitatively by means of an evaluation method that uses entropy as the basis for measuring the uniformity of pixel luminance within a segmentation region. Standard brain images from the IBSR database with manual segmentation results are considered.

Title: Image Modeling and Understanding via Fuzzy Transforms
Authors: Irina Perfilieva
Affiliation: Institute for Research and Applications of Fuzzy Modeling, University of Ostrava, Czech Republic
Abstract: The paper will be focused on new theoretical and application aspects of image processing in general and  advantage of fuzzy (soft computing) techniques in this field in particular.
    Together with perpetual development of soft computing methods, their applications in analysis and representation of images grow in numbers and establish stable and developing approach in this field of research. The explanation of this phenomenon is that we perceive images as meaningful entities and need tools to represent the immanent meaning formally. Therefore, the purpose of relevant representation is to make important aspects of physical objects explicit and by this, accessible for processing.
    There are many methods that are used in this step. A vast majority of them consider an image as a two-dimensional signal, and process it accordingly. As a result, the technique of Fourier transform is widely used, but leads to the situation where the connection between a problem and a method of its solution is lost.
    Contrary to this, we propose the method of fuzzy (F-) transform that is based on a fuzzy partition of a universe of discourse. The method allows us to stay in the same space where a problem is formulated and solved. The partition elements are fuzzy granules that connect a low-level representation with meaningful atomic structures. The F-transform technique can be explained in the language of discrete convolutions, scale-space representations, integral transforms and generally, aggregation operators. This fact emphasizes its high position among image processing tools.
    We discuss typical problems of image processing: compression, reconstruction, edge detection, and explain how these problems are formulated and solved in the language of F-transform components. Moreover, we propose a single technique that can be used for successful solution of all specified problems. Our last results in patter image recognition: matching, detection and tracking will be discussed too.

Title: Image Fusion with Aggregation Operators in Remote Sensing
Authors: Tiago M. A. Santos 1, André Mora 1, João M. N. Silva 2, António Falcao 1, José M. Fonseca 1 and Rita A. Ribeiro 1
Affiliations: 1 Computational Intelligence Group of CTS/UNINOVA, FCT / NOVA University of Lisbon, Portugal
2 CCIAM - Climate Change Impacts, Adaptation & Modelling research group, CE3C, FCUL, Lisboa, Portugal

Title: Identification of Atypical Pixels in Images through the Family of C-Means Partitional Clustering
Authors: B. Ojeda Magaña 1, J. Quintanilla Domínguez 2, L. Gómez-Barba 3, R. Ruelas 1, J. M. Barrón 1 and D. Andina 2
Affiliation: 1 Departamento de Ingeniería de Proyectos, Universidad de Guadalajara, Jalisco, Mexico.
2
Grupo de Automatización en Señal y Comunicaciones (GASC), Universidad Politécnica de Madrid (UPM), Madrid, Spain.
3 Doctorado en Tecnologías de Información, CUCEA, Universidad de Guadalajara, Jalisco, Mexico.
Abstract: Digital image segmentation continuous to be an interesting challenge, mainly due to the poor homogeneity of the objects in the images, objects that frequently are very small or that have several tonalities, among other features. In some real applications, the pixels of interest in the images are the less representative in quantity, and the corresponding objects can be ignored as the pixels are identified as atypical. For example, the pixels of micro-calcifications in mammograms, because these pixels are generally considered as part of the tissue in the breast. The partitional clustering algorithms, based on the c-Means family, have been applied to digital image segmentation, and it was demonstrated that they represent a suitable choice for this task. These methods provide hard, fuzzy, or possibilistic partitions of the segmented objects, and the two last ones give more information about the relationship between the pixels and the objects that they represent. So, this proposal presents an analysis of the c-Means clustering algorithms family, and the way to take a better profit of the information provided by each category of clustering algorithms. In this case regarding the application to digital image segmentation, especially for the identification of particular objects represented by atypical pixels, where some real cases are analyzed. Finally, a series of highlights are provided for the applications of the algorithms, and where the advantages and drawbacks of each category of algorithms are evaluated, in order to propose the best clustering technique for the identification of objects represented by atypical pixels.
Keywords: clustering; image processing; atypicality

Title: Medical Image Segmentation using Partitional Clustering Algorithms
Authors: Joel Quintanilla 1,*, Benjamín Ojeda 2, Ernesto García 1, Ismael Urbina 1, Andrés González 1 and
Rafael Guzmán 3
Affiliation: 1 Instituto Tecnológico Superior de Guanajuato, Carretera Guanajuato-Puentecillas km 10.5, Guanajuato, México.
2 Centro Universitario de Ciencias Exactas e Ingenierías, Universidad de Guadalajara, José Guadalupe Zuno
No. 48, Zapopan Jalisco, México.
3 División de Ingenierías Campus Irapuato-Salamanca, Universidad de Guanajuato, Carretera
Salamanca-Valle de Santiago km 3.5+1.8 Comunidad de Palo Blanco, Salamanca Guanajuato, México.
Abstract: In recent years a great diversity of image segmentation techniques have been proposed and have been widely used in different areas, such as: medical images analysis, teledetection, agriculture among others. This paper presents a methodology to detect regions that corresponds to microcalcifications and healthy tissue in regions of interest extracted from digitized mammograms. To carry out the detection an image processing tool known as segmentation is used. To perform the segmentation three partitional clustering algorithms most used in the image segmentation based on regions are applied. These algorithms are k-means, fuzzy c-means and possibilistic fuzzy c-means. The clustering is performed with the gray level intensity of the pixels of the images. The clustering algorithms are compared with the aim of observe which algorithm contribute to better segmentation of microcalcifications. The results show that the segmentation by means of partitional clustering algorithms are an effective way to segment regions that correspond to microcalcifications in the images and promises to be of great help in the medical images field.
Keywords: image processing; medical image segmentation; partitional clustering algorithms

Title: Seed castor shape analysis by clustering methods
Authors: J. M. Barrón-Adame * , M. S. Acosta-Navarrete , B. Ojeda-Magaña , Joel Quintanilla-Domínguez , A. Vega-Corona
Abstract: Image segmentation is the process of image partition into homogeneous regions that share certain visual characteristics. Identification and classification of objects in image allow an accurate description between them. This paper presents the comparative analysis of Fuzzy C-means (FCM) clustering and Self-Organizing Maps (SOM) network to segment color images. Results on FCM and SOM are compared with the classical K-means clustering. Image segmentation analysis is applied to six seed lines (nh1, nh2, nh3, nh4, nh5 and nh6) of castor to determine their morphological variation in size and shape. Simulation results show that SOM network performs better than FCM and K-Means.

Journal Contact

MDPI AG
Information Editorial Office
St. Alban-Anlage 66, 4052 Basel, Switzerland
E-Mail: 
Tel. +41 61 683 77 34
Fax: +41 61 302 89 18
Editorial Board
Contact Details Submit to Information Edit a special issue Review for Information
logo
loading...
Back to Top