Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
4.9
2.7
Journals
Symmetry
Special Issues
Symmetry in Vision II
share announcement

Symmetry in Vision II

A special issue of Symmetry (ISSN 2073-8994). This special issue belongs to the section "Computer".

Deadline for manuscript submissions: closed (29 December 2021) | Viewed by 16930

Special Issue Editors

Dr. Bernard Tiddeman

E-Mail Website
Guest Editor
Department of Computer Science, Aberystwyth University, Reception, Penglais, Aberystwyth, Ceredigion SY23 3FL, UK
Interests: computer vision and computer graphics; applications of computer vision in plant and marine biology; applications in digital heritage; texture analysis of faces; heart-rate estimation from video data; evolution and adaptation of artificial neural networks for vision problems in robotics; unsupervised image registration
Dr. D. Michael Burt

E-Mail Website
Guest Editor
Department of Psychology, Durham University, South Road, Durham DH1 3LE, UK
Interests: evolutionary psychology; facial expression recognition

Special Issue Information

Dear Colleagues,

Symmetry plays a central role in many vision systems, both natural and artificial. Vision systems need to work in a world that is left–right agnostic, so it should be robust to left–right flipping. Symmetry can be an important cue to biological fitness and facial expression recognition, so detecting symmetry, even in the presence of out-of-plane rotations, is a useful adaptive trait. In spite of the apparent value of symmetry in vision, biological visual processing shows a degree of lateralisation rather than the two hemispheres processing information in exactly the same manner. There appears to be a balance between the cost of maintaining duplicate and redundant visual processing in both hemispheres and the gains of differential specialisation. Understanding of this, presumably optimised, pattern’s processing abilities of the right and left hemispheres could lead to new or improved understanding of the function of symmetry in nature. Measurement of symmetry/asymmetry is important in a number of domains, including aesthetics, biometrics, health, biology research or manufacturing quality control. Exploiting symmetry can help to make the training or application of vision systems, such as deep convolutional neural networks, more efficient and the resulting systems more compact. This Special Issue is devoted to cutting edge studies on how symmetry is, or can be, measured and exploited by biological and artificial visual systems.

Please note that all submitted papers must be within the general scope of the Symmetry journal.

Dr. Bernard Tiddeman
Dr. D. Michael Burt
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 submissions that pass pre-check are 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. Symmetry 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 2400 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

  • symmetry
  • computer vision
  • lateralisation
  • deep learning
  • convolutional neural networks
  • evolutionary psychology

Published Papers (5 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

17 pages, 17990 KiB  
Article
Principal Component Wavelet Networks for Solving Linear Inverse Problems
by Bernard Tiddeman and Morteza Ghahremani
Symmetry 2021, 13(6), 1083; https://doi.org/10.3390/sym13061083 - 17 Jun 2021
Cited by 3 | Viewed by 1730
Abstract
In this paper we propose a novel learning-based wavelet transform and demonstrate its utility as a representation in solving a number of linear inverse problems—these are asymmetric problems, where the forward problem is easy to solve, but the inverse is difficult and often [...] Read more.
In this paper we propose a novel learning-based wavelet transform and demonstrate its utility as a representation in solving a number of linear inverse problems—these are asymmetric problems, where the forward problem is easy to solve, but the inverse is difficult and often ill-posed. The wavelet decomposition is comprised of the application of an invertible 2D wavelet filter-bank comprising symmetric and anti-symmetric filters, in combination with a set of 1×1 convolution filters learnt from Principal Component Analysis (PCA). The 1×1 filters are needed to control the size of the decomposition. We show that the application of PCA across wavelet subbands in this way produces an architecture equivalent to a separable Convolutional Neural Network (CNN), with the principal components forming the 1×1 filters and the subtraction of the mean forming the bias terms. The use of an invertible filter bank and (approximately) invertible PCA allows us to create a deep autoencoder very simply, and avoids issues of overfitting. We investigate the construction and learning of such networks, and their application to linear inverse problems via the Alternating Direction of Multipliers Method (ADMM). We use our network as a drop-in replacement for traditional discrete wavelet transform, using wavelet shrinkage as the projection operator. The results show good potential on a number of inverse problems such as compressive sensing, in-painting, denoising and super-resolution, and significantly close the performance gap with Generative Adversarial Network (GAN)-based methods. Full article
(This article belongs to the Special Issue Symmetry in Vision II)
►▼ Show Figures

Figure 1

24 pages, 4080 KiB  
Article
Multi-Scale and Multi-Branch Convolutional Neural Network for Retinal Image Segmentation
by Yun Jiang, Wenhuan Liu, Chao Wu and Huixiao Yao
Symmetry 2021, 13(3), 365; https://doi.org/10.3390/sym13030365 - 24 Feb 2021
Cited by 12 | Viewed by 2117
Abstract
The accurate segmentation of retinal images is a basic step in screening for retinopathy and glaucoma. Most existing retinal image segmentation methods have insufficient feature information extraction. They are susceptible to the impact of the lesion area and poor image quality, resulting in [...] Read more.
The accurate segmentation of retinal images is a basic step in screening for retinopathy and glaucoma. Most existing retinal image segmentation methods have insufficient feature information extraction. They are susceptible to the impact of the lesion area and poor image quality, resulting in the poor recovery of contextual information. This also causes the segmentation results of the model to be noisy and low in accuracy. Therefore, this paper proposes a multi-scale and multi-branch convolutional neural network model (multi-scale and multi-branch network (MSMB-Net)) for retinal image segmentation. The model uses atrous convolution with different expansion rates and skip connections to reduce the loss of feature information. Receiving domains of different sizes captures global context information. The model fully integrates shallow and deep semantic information and retains rich spatial information. The network embeds an improved attention mechanism to obtain more detailed information, which can improve the accuracy of segmentation. Finally, the method of this paper was validated on the fundus vascular datasets, DRIVE, STARE and CHASE datasets, with accuracies/F1 of 0.9708/0.8320, 0.9753/0.8469 and 0.9767/0.8190, respectively. The effectiveness of the method in this paper was further validated on the optic disc visual cup DRISHTI-GS1 dataset with an accuracy/F1 of 0.9985/0.9770. Experimental results show that, compared with existing retinal image segmentation methods, our proposed method has good segmentation performance in all four benchmark tests. Full article
(This article belongs to the Special Issue Symmetry in Vision II)
►▼ Show Figures

Figure 1

36 pages, 10685 KiB  
Article
An Improved Local Search Genetic Algorithm with a New Mapped Adaptive Operator Applied to Pseudo-Coloring Problem
by Monique Simplicio Viana, Orides Morandin Junior and Rodrigo Colnago Contreras
Symmetry 2020, 12(10), 1684; https://doi.org/10.3390/sym12101684 - 14 Oct 2020
Cited by 7 | Viewed by 1870
Abstract
In many situations, an expert must visually analyze an image arranged in grey levels. However, the human eye has strong difficulty in detecting details in this type of image, making it necessary to use artificial coloring techniques. The pseudo-coloring problem (PsCP) consists of [...] Read more.
In many situations, an expert must visually analyze an image arranged in grey levels. However, the human eye has strong difficulty in detecting details in this type of image, making it necessary to use artificial coloring techniques. The pseudo-coloring problem (PsCP) consists of assigning to a grey-level image, pre-segmented in K sub-regions, a set of K colors that are as dissimilar as possible. This problem is part of the well-known class of NP-Hard problems and, therefore, does not present an exact solution for all instances. Thus, meta-heuristics has been widely used to overcome this problem. In particular, genetic algorithm (GA) is one of those techniques that stands out in the literature and has already been used in PsCP. In this work, we present a new method that consists of an improvement of the GA specialized in solving the PsCP. In addition, we propose the addition of local search operators and rules for adapting parameters based on symmetric mapping functions to avoid common problems in this type of technique such as premature convergence and inadequate exploration in the search space. Our method is evaluated in three different case studies: the first consisting of the pseudo-colorization of real-world images on the RGB color space; the second consisting of the pseudo-colorization in RGB color space considering synthetic and abstract images in which its sub-regions are fully-connected; and the third consisting of the pseudo-colorization in the Munsell atlas color set. In all scenarios, our method is compared with other state-of-the-art techniques and presents superior results. Specifically, the use of mapped automatic adjustment operators proved to be powerful in boosting the proposed meta-heuristic to obtain more robust results in all evaluated instances of PsCP in all the considered case studies. Full article
(This article belongs to the Special Issue Symmetry in Vision II)
►▼ Show Figures

Figure 1

21 pages, 4514 KiB  
Article
3D-MRI Brain Tumor Detection Model Using Modified Version of Level Set Segmentation Based on Dragonfly Algorithm
by Hassan A. Khalil, Saad Darwish, Yasmine M. Ibrahim and Osama F. Hassan
Symmetry 2020, 12(8), 1256; https://doi.org/10.3390/sym12081256 - 29 Jul 2020
Cited by 44 | Viewed by 7765
Abstract
Accurate brain tumor segmentation from 3D Magnetic Resonance Imaging (3D-MRI) is an important method for obtaining information required for diagnosis and disease therapy planning. Variation in the brain tumor’s size, structure, and form is one of the main challenges in tumor segmentation, and [...] Read more.
Accurate brain tumor segmentation from 3D Magnetic Resonance Imaging (3D-MRI) is an important method for obtaining information required for diagnosis and disease therapy planning. Variation in the brain tumor’s size, structure, and form is one of the main challenges in tumor segmentation, and selecting the initial contour plays a significant role in reducing the segmentation error and the number of iterations in the level set method. To overcome this issue, this paper suggests a two-step dragonfly algorithm (DA) clustering technique to extract initial contour points accurately. The brain is extracted from the head in the preprocessing step, then tumor edges are extracted using the two-step DA, and these extracted edges are used as an initial contour for the MRI sequence. Lastly, the tumor region is extracted from all volume slices using a level set segmentation method. The results of applying the proposed technique on 3D-MRI images from the multimodal brain tumor segmentation challenge (BRATS) 2017 dataset show that the proposed method for brain tumor segmentation is comparable to the state-of-the-art methods. Full article
(This article belongs to the Special Issue Symmetry in Vision II)
►▼ Show Figures

Graphical abstract

12 pages, 4095 KiB  
Article
Structured Light 3D Reconstruction System Based on a Stereo Calibration Plate
by Meiying Li, Jin Liu, Haima Yang, Wanqing Song and Zihao Yu
Symmetry 2020, 12(5), 772; https://doi.org/10.3390/sym12050772 - 7 May 2020
Cited by 4 | Viewed by 2688
Abstract
Calibration is a critical step in structured light 3D imaging systems. However, in the traditional calibration process, since the calibration plate is based on a two-dimensional model, the flatness of the calibration plate and the angle of the photo will affect the subsequent [...] Read more.
Calibration is a critical step in structured light 3D imaging systems. However, in the traditional calibration process, since the calibration plate is based on a two-dimensional model, the flatness of the calibration plate and the angle of the photo will affect the subsequent stitching steps based on the feature points. The number of photos also affects the calibration results. To improve the calibration accuracy, multiple photos need to be taken. The primary objective of this study was to achieve the simple and fast calibration of system parameters, so a method obtaining a large number of calibration data by homography matrix is presented, and a corresponding stereo target is designed in symmetry. First, using the relationship between the corner coordinates of the left and right parts of the stereo calibration plate and the coordinates of the world coordinate system, the homography matrix of the left and right calibration plates from the image coordinates to the world coordinates is calculated. Second, all the pixels in the stereo calibration plate are matched to the world coordinate system by using the homography matrix. In addition, we also compared the results of this method with those of traditional calibration methods. The experimental results show that the 3D geometric surface of the reconstruction result is smooth, it avoids the missing parts and the visual effect is excellent. Furthermore, the error range of small and complex objects can be reduced to 0.03 mm~0.05 mm. This method simplifies the calibration steps, reduces the calibration costs and has practical application value. Full article
(This article belongs to the Special Issue Symmetry in Vision II)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-5
Back to TopTop