Vision is the complex process of deriving meaning from what is seen. The fields of computer vision and image processing have tried to automate tasks that the human visual system can do, with the aim of gaining a high-level understanding of images and videos. Computer vision algorithms have been successfully applied to a large number of real-world problems ranging from remote sensing to medical image analysis, video surveillance, human-robot interaction, and computer-aided design. In turn, evolutionary computation methods have been shown to be more efficient than classical optimization approaches for discontinuous, non-differentiable, multimodal and noisy problems. They have also demonstrated their ability as robust approaches to cope with the fundamental steps of the computer vision and image processing pipeline (e.g. restoration, segmentation, registration, or tracking). As a result of the convergence of the computer vision and evolutionary computation research fields, a large number of research activities have arisen in the last two decades.
Scope and Topics
The proposed special session aims to bring together theories and applications of evolutionary computation techniques to computer vision and image processing problems. In this sense, this special session aims to be a meeting place for researchers in the fields of computer vision and/or evolutionary computation, with the aim of enriching both disciplines by means of the hybridization of state-of-the-art approaches from those domains. Topics of interest include, but are not limited to:
- New theories and methods in the application of evolutionary computation paradigms to computer vision and image processing problems.
- Evolutionary computation paradigms include
- genetic algorithms,
- genetic programming,
- evolutionary strategies,
- evolutionary programming,
- particle swarm optimization,
- ant colony optimization,
- and differential evolution, among many others (including single- and multi-objective optimization algorithms).
- Potential applications in computer vision and image processing include
- image segmentation
- image registration
- image restoration
- image feature extraction
- visual scene analysis
- object detection and classification
- handwritten digit recognition
- object tracking
- face detection and identification
- texture image analysis
- human activity recognition
- robot vision
- and 3D scene reconstruction, among many others.
- Evolutionary computation paradigms include
- Given the huge impact of deep learning in the computer vision community, especially from 2012, and the astonishing performance provided by deep learning algorithms in computer vision tasks, cross-fertilization of evolutionary computation and deep or shallow neural networks applied to vision tasks is especially encouraged. This includes research in transfer learning and domain adaptation, as well as new training strategies based on evolutionary computation techniques, and any hybridization of evolutionary computation with
- multi-layer perceptrons,
- adversarial networks,
- Boltzmann machines,
- Hopfield networks,
- deep belief networks,
- neural Turing machines,
- convolutional neural networks,
- and recurrent neural networks, among many other neural models.
- Hybridizations of evolutionary computation methods and other computational intelligence and machine learning techniques (e.g. fuzzy systems, reinforcement learning, artificial immune systems, and learning classifier systems), applied to computer vision and image processing tasks are also encouraged.
- Paper Submission Deadline: 15 Jan 2019
- Notification of Acceptance: 15 Mar 2019
- Final Paper Submission Deadline: 15 Apr 2019
Papers for IEEE CEC 2019 should be submitted electronically through the Congress website at http://cec2019.org/, and will be refereed by experts in the fields and ranked based on the criteria of originality, significance, quality and clarity. To submit your papers to the special session, please select the Special Session name in the Main Research topic.
For more submission information please visit: http://cec2019.org/ All accepted papers will be published in the IEEE CEC 2019 electronic proceedings, included in the IEEE Xplore digital library, and indexed by EI Compendex.
Special Session Organizers
Pablo Mesejo (School of Computer Science, University of Granada, Spain)
Pablo Mesejo received the M.Sc. and Ph.D. degrees in computer science respectively from University of Coruña (Spain) and University of Parma (Italy), where he was an Early Stage Researcher within the Marie Curie ITN MIBISOC ("Medical Imaging using Bio-inspired and Soft Computing"). He was a post-doctoral researcher at the ALCoV team of University of Auvergne (France) and the Mistis team of Inria Grenoble Rhône-Alpes (France), before joining the Perception team with an Inria Starting Researcher Position. He currently is a Marie Curie Experienced Researcher at the University of Granada (Spain). He is chair of the IEEE Computational Intelligence Society Task Force on Evolutionary Computer Vision and Image Processing, and co-founder and scientific advisor of Panacea Cooperative Research S.Coop., a recently created SME focused on finding intelligent solutions aimed at solving unmet biomedical needs. His research interests include computer vision, machine learning and computational intelligence techniques mainly applied to biomedical image analysis problems.
Harith Al-Sahaf (School of Engineering and Computer Science, Victoria University of Wellington, New Zealand)
Harith Al-Sahaf received the B.Sc. degree in computer science from Baghdad University (Iraq), in 2005. He joined the Victoria University of Wellington (VUW), (New Zealand) in July 2007 where he received his MCompSc and PhD degrees in Computer Science in 2010 and 2017, respectively. In October 2016, he has joined the School of Engineering and Computer Science, VUW as a Post-doctoral Research Fellow and as a full-time lecturer since September 2018. His current research interests include evolutionary computation, particularly genetic programming, computer vision, pattern recognition, evolutionary cybersecurity, machine learning, feature manipulation including feature detection, selection, extraction and construction, transfer learning, domain adaptation, one-shot learning, and image understanding. He is a member of the IEEE CIS ETTC Task Force on Evolutionary Computer Vision and Image Processing, the IEEE CIS ETTC Task Force on Evolutionary Computation for Feature Selection and Construction, the IEEE CIS ISATC Task Force on Evolutionary Deep Learning and Applications, and the IEEE CIS ISATC Intelligent Systems for Cybersecurity.
Youssef S.G. Nashed (Argonne National Laboratory, United States)
Youssef Nashed is an assistant computer scientist at the Mathematics and Computer Science Division in Argonne National Laboratory, USA, and a fellow at the Northwestern Argonne Institute for Science and Engineering. He is involved in multiple projects with the Advanced Photon Source to develop High Performance Computing solutions to x-ray image reconstruction problems. He received his PhD degree from the University of Parma, Italy, in 2013, where he focused on real-time detection and classification of patterns in images and videos, employing evolutionary algorithms and methods based on the human visual cortex. He is also the author of various open source software libraries for image reconstruction, GPU-¬based metaheuristics, data analysis and visualization. His research interests are in large-scale scientific data analysis and visualization, real-time image processing, machine learning on parallel and distributed architectures, and image reconstruction algorithmic development.
Program Committee (to be confirmed)
- Stefano Cagnoni (University of Parma, Italy)
- Óscar Cordón (University of Granada, Spain)
- Sergio Damas (University of Granada, Spain)
- Eli David (Bar-Ilan University, Israel)
- Ivanoe De Falco (ICAR-CNR, Italy)
- Antonio Della Cioppa (University of Salerno, Italy)
- Francesco Fontanella (University of Cassino and Southern Lazio, Italy)
- Óscar Ibáñez (Panacea Cooperative Research, Spain)
- Mario Köppen (Kyushu Institute of Technology, Japan)
- Krzysztof Krawiec (Poznan University of Technology, Poland)
- Evelyne Lutton (INRA, France)
- Amir Nakib (University of Paris-Est, France)
- Gustavo Olague (CICESE, Mexico)
- Clara Pizzuti (ICAR-CNR, Italy)
- Kai Qin (Swinburne University of Technology, Australia)
- Alessandra Scotto di Freca (University of Cassino and Southern Lazio, Italy)
- Stephen L. Smith (University of York, UK)
- Andy Song (RMIT University, Australia)
- Yanan Sun (Victoria University of Wellington, New Zealand)
- Bing Xue (Victoria University of Wellington, New Zealand)
- Mengjie Zhang (Victoria University of Wellington, NZ)