Image Enhancement, Modeling and Visualization

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

Deadline for manuscript submissions: closed (12 August 2018) | Viewed by 34630

Special Issue Editors


E-Mail Website
Guest Editor
Department of Computer Science, University of Milano, 20122 Milano, Italy
Interests: computational models of color vision; image unsupervised enhancement and restoration; HDR imaging; color vision; digital imaging

E-Mail Website
Guest Editor
Research Unit Technologies of Vision, Fondazione Bruno Kessler (FBK), 38123 Trento, Italy
Interests: machine vision; color image processing; image enhancement; image retrieval; object detection and recognition; hardware oriented image processing

E-Mail Website
Guest Editor
Department of Computer Science, University of Milano, 20122 Milano, Italy
Interests: color perception; image difference metrics; image quality; image enhancement; swarm intelligence for image processing; contrast measuring; spatial color algorithms

E-Mail Website
Guest Editor
Department of Electronic Systems and Information Processing, University of Zagreb, 10000 Zagreb, Croatia
Interests: brightness adjustment; color constancy; HDR; illumination estimation; image enhancement; Retinex; tone mapping; white balancing

Special Issue Information

Dear Colleagues,

The current, wide diffusion of new technological devices, such as RGB-D, HDR and thermal cameras, smart and multi-medial vision sensors, 3D virtual reality visors, Google glasses, urgently requires adaptation and/or renewal of the image processing approach. In this framework, image enhancement, vision modelling and novel visualization techniques and devices are important key factors. One of the challenges is to automatically integrate and process the multimedia data collected by the new-generation devices in order to provide high-quality information. To this aim, modern image enhancement methods and visualization techniques are at the base of this research: They must account for the application at hand, for the physical, hardware characteristics of the acquisition device, and especially for different, often multi-dimensional features, including, for instance, color, distance, time information, or even non-visual cues, like textual labels or audio.

There is an actual need for supporting these emerging novel techniques with more effective vision models. The scientific community has known since the 1970s that human vision is a spatial process, now it is time to take advantage of this knowledge for the next generation of image enhancement and visualization techniques.

This Special Issue intends to provide a comprehensive overview of recent, theoretical and/or practical advances and new trends in image enhancement, vision modelling applied to image processing and advanced visualization methods and devices, and to discuss their applications to computer vision, image processing and understanding. 

Prof. Alessandro Rizzi
Ms. Michela Lecca
Dr. Gabriele Simone
Dr. Nikola Banic
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. 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 1800 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

  • Image enhancement
  • Image processing
  • Hardware oriented Image Processing (signal-processing aspects for image processing, device dependent image processing, computer vision algorithms for smart cameras)
  • Bio-inspired Image Processing
  • Contrast enhancement
  • Noise Removal ,Demosaicing, and Filters
  • Image Compression
  • Image restoration
  • Image Quality Assessment
  • Vision modeling
  • Color, textures and visual features
  • Visualization
  • HDR
  • RGB-D Image Processing
  • Hyperspectral and Thermal Imaging
  • Multimedia
  • 3D Modelling and Rendering
  • Visual Processing in Augmented Reality
  • Benchmarks
  • Applications and New Trends

Published Papers (5 papers)

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

Research

18 pages, 11373 KiB  
Article
Laser Scanners for High-Quality 3D and IR Imaging in Cultural Heritage Monitoring and Documentation
by Sofia Ceccarelli, Massimiliano Guarneri, Mario Ferri de Collibus, Massimo Francucci, Massimiliano Ciaffi and Alessandro Danielis
J. Imaging 2018, 4(11), 130; https://doi.org/10.3390/jimaging4110130 - 5 Nov 2018
Cited by 23 | Viewed by 5253
Abstract
Digital tools as 3D (three-dimensional) modelling and imaging techniques are having an increasing role in many applicative fields, thanks to some significative features, such as their powerful communicative capacity, versatility of the results and non-invasiveness. These properties are very important in cultural heritage, [...] Read more.
Digital tools as 3D (three-dimensional) modelling and imaging techniques are having an increasing role in many applicative fields, thanks to some significative features, such as their powerful communicative capacity, versatility of the results and non-invasiveness. These properties are very important in cultural heritage, and modern methodologies provide an efficient means for analyzing deeply and virtually rendering artworks without contact or damage. In this paper, we present two laser scanner prototypes based on the Imaging Topological Radar (ITR) technology developed at the ENEA Research Center of Frascati (RM, Italy) to obtain 3D models and IR images of medium/large targets with the use of laser sources without the need for scaffolding and independently from illumination conditions. The RGB-ITR (Red Green Blue-ITR) scanner employs three wavelengths in the visible range for three-dimensional color digitalization up to 30 m, while the IR-ITR (Infrared-ITR) system allows for layering inspection using one IR source for analyses. The functionalities and operability of the two systems are presented by showing the results of several case studies and laboratory tests. Full article
(This article belongs to the Special Issue Image Enhancement, Modeling and Visualization)
Show Figures

Figure 1

11 pages, 1210 KiB  
Article
Green Stability Assumption: Unsupervised Learning for Statistics-Based Illumination Estimation
by Nikola Banić and Sven Lončarić
J. Imaging 2018, 4(11), 127; https://doi.org/10.3390/jimaging4110127 - 29 Oct 2018
Cited by 9 | Viewed by 4254
Abstract
In the image processing pipeline of almost every digital camera, there is a part for removing the influence of illumination on the colors of the image scene. Tuning the parameter values of an illumination estimation method for maximal accuracy requires calibrated images with [...] Read more.
In the image processing pipeline of almost every digital camera, there is a part for removing the influence of illumination on the colors of the image scene. Tuning the parameter values of an illumination estimation method for maximal accuracy requires calibrated images with known ground-truth illumination, but creating them for a given sensor is time-consuming. In this paper, the green stability assumption is proposed that can be used to fine-tune the values of some common illumination estimation methods by using only non-calibrated images. The obtained accuracy is practically the same as when training on calibrated images, but the whole process is much faster since calibration is not required and thus time is saved. The results are presented and discussed. The source code website is provided in Section Experimental Results. Full article
(This article belongs to the Special Issue Image Enhancement, Modeling and Visualization)
Show Figures

Figure 1

21 pages, 8051 KiB  
Article
An Uncertainty-Aware Visual System for Image Pre-Processing
by Christina Gillmann, Pablo Arbelaez, Jose Tiberio Hernandez, Hans Hagen and Thomas Wischgoll
J. Imaging 2018, 4(9), 109; https://doi.org/10.3390/jimaging4090109 - 10 Sep 2018
Cited by 10 | Viewed by 4901
Abstract
Due to image reconstruction process of all image capturing methods, image data is inherently affected by uncertainty. This is caused by the underlying image reconstruction model, that is not capable to map all physical properties in its entirety. In order to be aware [...] Read more.
Due to image reconstruction process of all image capturing methods, image data is inherently affected by uncertainty. This is caused by the underlying image reconstruction model, that is not capable to map all physical properties in its entirety. In order to be aware of these effects, image uncertainty needs to be quantified and propagated along the entire image processing pipeline. In classical image processing methodologies, pre-processing algorithms do not consider this information. Therefore, this paper presents an uncertainty-aware image pre-processing paradigm, that is aware of the input image’s uncertainty and propagates it trough the entire pipeline. To accomplish this, we utilize rules for transformation and propagation of uncertainty to incorporate this additional information with a variety of operations. Resulting from this, we are able to adapt prominent image pre-processing algorithms such that they consider the input images uncertainty. Furthermore, we allow the composition of arbitrary image pre-processing pipelines and visually encode the accumulated uncertainty throughout this pipeline. The effectiveness of the demonstrated approach is shown by creating image pre-processing pipelines for a variety of real world datasets. Full article
(This article belongs to the Special Issue Image Enhancement, Modeling and Visualization)
Show Figures

Figure 1

9 pages, 33273 KiB  
Article
Use of an Occlusion Mask for Veiling Glare Removal in HDR Images
by Federico Cozzi, Carmine Elia, Giovanni Gerosa, Filippo Rocchetta, Matteo Lanaro and Alessandro Rizzi
J. Imaging 2018, 4(8), 100; https://doi.org/10.3390/jimaging4080100 - 3 Aug 2018
Cited by 4 | Viewed by 4991
Abstract
Optical systems in digital cameras present a limit during the acquisition of standard and High Dynamic Range Images (HDRI) due to the presence of veiling glare, an artifact caused by an unwanted spread of the source of light. In this paper, we analyze [...] Read more.
Optical systems in digital cameras present a limit during the acquisition of standard and High Dynamic Range Images (HDRI) due to the presence of veiling glare, an artifact caused by an unwanted spread of the source of light. In this paper, we analyze the state-of-the-art of veiling glare removal in HDRI, giving attention to the paper presented by Talvala. Then we describe an algorithm for veiling glare removal based on the same occlusion mask, to study the benefits provided by it in HDRI acquisition process. Finally, we demonstrate the efficiency of the occlusion mask method in veiling glare removal without any post production estimation and subtraction. Full article
(This article belongs to the Special Issue Image Enhancement, Modeling and Visualization)
Show Figures

Figure 1

18 pages, 13685 KiB  
Article
Evaluating the Performance of Structure from Motion Pipelines
by Simone Bianco, Gianluigi Ciocca and Davide Marelli
J. Imaging 2018, 4(8), 98; https://doi.org/10.3390/jimaging4080098 - 1 Aug 2018
Cited by 134 | Viewed by 14213
Abstract
Structure from Motion (SfM) is a pipeline that allows three-dimensional reconstruction starting from a collection of images. A typical SfM pipeline comprises different processing steps each of which tackles a different problem in the reconstruction pipeline. Each step can exploit different algorithms to [...] Read more.
Structure from Motion (SfM) is a pipeline that allows three-dimensional reconstruction starting from a collection of images. A typical SfM pipeline comprises different processing steps each of which tackles a different problem in the reconstruction pipeline. Each step can exploit different algorithms to solve the problem at hand and thus many different SfM pipelines can be built. How to choose the SfM pipeline best suited for a given task is an important question. In this paper we report a comparison of different state-of-the-art SfM pipelines in terms of their ability to reconstruct different scenes. We also propose an evaluation procedure that stresses the SfM pipelines using real dataset acquired with high-end devices as well as realistic synthetic dataset. To this end, we created a plug-in module for the Blender software to support the creation of synthetic datasets and the evaluation of the SfM pipeline. The use of synthetic data allows us to easily have arbitrarily large and diverse datasets with, in theory, infinitely precise ground truth. Our evaluation procedure considers both the reconstruction errors as well as the estimation errors of the camera poses used in the reconstruction. Full article
(This article belongs to the Special Issue Image Enhancement, Modeling and Visualization)
Show Figures

Figure 1

Back to TopTop