Citare Marginean, R., Andreica, A., Diosan, L., Bálint, Z., Stochastic remote neighborhoods control GrowCut’s segmentation semanticsMECO45 45th Conference of the Middle European Cooperation in Statistical Physics , 2020
We present a new type of optimization algorithms, adapted for neural network training. These algorithms are based upon sequential operator splitting technique for some associated dynamical systems. Furthermore, we investigate through numerical simulations the empirical rate of convergence of these iterative schemes toward a local minimum of the loss function, with some suitable choices…
This paper proposes a novel method for supervised optimization of cellular automata rules using curriculum learning. The optimized edge detector manages to generalize a rule from synthetic data that is applicable to magnetic resonance images, removing the need for manual annotation of medical data. The method achieves competitive results with classical edge detectors on…
Edge detection is an important component in many computer vision tasks since edges convey information about the objects in an image. This paper presents a comparative analysis of the proposed edge detector with respect to one of the state-of-the-art methods, the Canny edge detector. Our edge detection model involves the supervised optimization of a…
Citare Mărginean, R., Manole, S., Popa, L., Coman, M., Pop, S., Budurea, C., Andreica, A., Dioşan, L., Bálint, Z., Initial validation of an automatic algorithm for whole heart segmentation from cardiac MRI images using atrial volume determination, European congress of radiology (ECR 2020) https://www.myesr.org/congress
Edge detection is a fundamental image analysis task, as it provides insight on the content of an image. There are weaknesses in some of the edge detectors developed until now, such as disconnected edges, the impossibility to detect branching edges, or the need for a ground truth that is not always accessible. Therefore, a…
Despite the promising results obtained by deep learning methods in the field of medical image segmentation, lack of sufficient data always hinders performance to a certain degree. In this work, we explore the feasibility of applying deep learning methods on a pilot dataset. We present a simple and practical approach to perform segmentation in…
We present a method of using interactive image segmentation algorithms to reduce specific image segmentation problems to the task of finding small sets of pixels identifying the regions of interest. To this end, we empirically show the feasibility of automatically generating seeds for GrowCut, a popular interactive image segmentation algorithm. The principal contribution of…
Abstract As the world changes, so does the future of our students. In this respect, the evolution of the technology comes up with specific environments for educational purpose. Building smart learning environments supported by e-learning platforms is an important area of research in education domain within our days. The evolution of these smart learning…
Abstract Looking back to the rumours from the early 2000’s, when the world of technology bloomed together with the curiosity towards what was next to come, by 2020, robots should have assisted and supported almost every task from our daily life. While this may seem as a Sci-Fi movie scenario, it is partially a…