Convolutional Neural Networks for Visual Detection, Recognition and Segmentation in Images and Videos

Dear Colleagues,

We are inviting submissions to the Special Issue on "Convolutional Neural Networks for Visual Detection, Recognition and Segmentation in Images and Videos".

The amount of visual data collected and generated has been rising over the world, and the automatic recognition of the events in these visual data has become important and challenging problem for the research community. Visual recognition with human effort is a time-consuming, tedious, inefficient, and costly. Therefore, it is necessary to decrease manual human efforts, and automated intelligent systems play an important role in solving visual-based problems. In the last decade, Convolutional Neural Network (CNN)-based computational intelligence algorithms have been shown to outperform state-of-the-art machine learning methods such as k-nearest neighbor, neural networks, and support vector machine. It may also be required to develop and employ a hybrid system combining CNN-based models with artificial intelligence techniques (e.g., support vector machine, random forests, etc.) to resolve a visual problem in images and videos. This Special Issue offers an opportunity for researchers to address broad challenges on both theoretical and application aspects of CNN-based architectures in image and video processing.

The main objective of this Special Issue is to discover and examine theory and application of CNN-based deep learning architectures for the problems in image and video applications. We invite researchers to contribute original research and review articles that will motivate the continuing effort on the application of Convolutional Neural Network frameworks to resolve image and video processing problems. The topics of this Special Issue on “Convolutional Neural Networks for Visual Recognition, Detection and Segmentation in Images and Videos” explicitly include (but are not limited to) the following aspects:

• convolutional neural networks;
• evolutionary deep learning models;
• big image and video datasets;
• deep-learning-based image/video processing;
• hybrid deep learning models;
• parallel deep convolutional neural networks;
• deep-learning-based object detection and recognition in images and videos;
• deep-learning-based object tracking;
• image and video segmentation;
• deep CNN-based real-time video processing;
• expert systems;
• applications of convolutional autoencoder in images and videos;
• applications of convolutional and generative adversarial networks.

Dr. Hüseyin Kusetogullari
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 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 250 words) can be sent to the Editorial Office for assessment.

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. Electronics is an international peer-reviewed open access semimonthly 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.