2D/3D image registration to align a 3D volume and 2D X-ray images is a challenging problem due to its ill-posed nature and various artifacts presented in 2D X-ray images. In this paper, we propose a multi-agent system with an auto attention mechanism for robust and efficient 2D/3D image registration. Specifically, an individual agent is trained with dilated Fully Convolutional Network (FCN) to ...

Two models based on convolutional neural networks are trained to predict the two-dimensional instantaneous velocity-fluctuation fields at different wall-normal locations in a turbulent open-channel flow, using wall-shear-stress components and wall pressure as inputs. The first model is fully network (FCN) which directly predicts fluctuations, while second one reconstructs flow linear combinatio...

Ultrasonic methods have great potential applications to detect and characterize defects in multi-layered bonded composites. However, it remains challenging quantitatively reconstruct defects, such as disbonds, that influence the integrity of adhesive bonds seriously reduce strength assemblies. In this work, an ultrasonic method based on supervised fully convolutional network (FCN) is proposed h...

Statistical approach for detection and estimation of parameters of short-term quasiperiodic processes was used in order to investigate the Free Core Nutation (FCN) signal in the Celestial Pole Offset (CPO). The results show that this signal is very unstable and that it disappeared in year 2000. The amplitude of oscillation with period of about 435 days is larger for dX as compared with that for...

Dermoscopy image detection stays a tough task due to the weak distinguishable property of the object.Although the deep convolution neural network signifigantly boosted the performance on prevelance computer vision tasks in recent years,there remains a room to explore more robust and precise models to the problem of low contrast image segmentation.Towards the challenge of Lesion Segmentation in ...

Abstract. Fully convolutional neural networks (FCN) are successfully used for pixel-wise land cover classification - the task of identifying physical material Earth’s surface every pixel in an image. The acquisition large training datasets is challenging, especially remote sensing, but necessary a FCN to perform well. One way circumvent manual labelling usage existing databases, which usually c...