Journal Menu► ▼ Journal Menu
Journal Browser► ▼ Journal Browser
Special Issue "Entropy in Image Analysis II"
Deadline for manuscript submissions: 20 December 2019.
Department of Applied Science and Technology, Polytechnic University of Turin, Turin, Italy
Interests: general physics and mathematics; optics; software; image processing applied to microscopy and satellite imagery
Special Issues and Collections in MDPI journals
Special Issue in Entropy: Entropy in Image Analysis
Special Issue in Entropy: Entropy and Information in Networks, from Societies to Cities
Special Issue in Geosciences: Image processing and satellite imagery analysis in environments
Image analysis is a fundamental task for extracting information from images acquired across a range of different devices. This analysis often needs numerical and analytical methods that are highly sophisticated, particularly for those applications in medicine, security, and remote sensing where the results of the processing consist of data of vital importance.
Since it is involved in numerous applications requiring reliable quantitative results, image analysis has produced a large number of approaches and algorithms, sometimes limited to specific functions in a small range of tasks, sometimes generic enough to be applied to a wide range of tasks. In this framework, a key role can be played by entropy, in the form of Shannon entropy or generalized entropy, used directly in processing methods or in the evaluation of results, to maximize the success of a final decision support system.
Since active research in image processing is still engaged in the search for methods that are truly comparable to the abilities of human vision capabilities, I solicit your contribution to this Special Issue of this journal, which is devoted to the use of entropy in extracting information from images and to the decision processes related to image analyses.
Dr. Amelia Carolina Sparavigna
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. Entropy 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.
- Image entropy
- Shannon entropy
- Tsallis entropy
- Generalized entropies
- Image processing
- Image segmentation
- Retinex methods
- Medical imaging
- Remote sensing
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: Pattern Classification Based Lossless Compression of Red Blood Cell Images of Malaria Infection Using Deep Learning
Authors: Y. Dong, W. D. Pan and D. Wu
Affiliation: University of Alabama in Huntsville, AL 35899, USA
Abstract: Malaria occurs in nearly 100 countries worldwide and imposes a huge toll on human health and heavy socioeconomic burdens. There is a notable challenge in telemedicine on efficient storage and rapid transfer of massive malaria infection image datasets for malaria infection. To this end, we propose a novel lossless compression method for red blood cell images by integrating compression with pattern classification based on stacked autoencoders. Our previous study on using autoencoders as a deep learning method to losslessly compress image datasets showed the advantage of exploiting in-class correlations by training the autoencoders using the images known to belong to the same class. However, the compression performance suffers if the images used for training come from different classes. Therefore, in this work, we introduce a more realistic framework where the input images are first classified before being compressed using autoencoders. We study how the accuracy of the classifiers would affect the overall compression ratios for two-class image dataset compression. We conduct information- theoretic analysis based on probabilistic distributions of the prediction residues, and derive formulas for compressed bit rates as a function of classification accuracies. We then use synthesized data based on the models to verify the theoretical results. Next, we use real malaria infection image datasets to evaluate the relations between classification accuracies and compressed bit rates. Simulation results show that the joint classification/compression method can achieve more efficient compression than other traditional lossless compression methods, such as JPEG2000, JPEG-LS, CALIC, and WebP.