Image acquisition techniques introduce various types of artifacts and noise such as additive white gaussian noise, salt and pepper noise etc, so image denoising is an essential preprocessing step in digital image processing. It is clear from the background study of denoising, conventional methods are not much effective in reducing the noise in the image. In this work, a novel approach which int...

Hepatocellular carcinoma (HCC) is a primary malignant tumor of the liver that accounts for an important health problem worldwide. Only 10-15% of HCC patients are suitable candidates for hepatic resection and liver transplantation due to the advanced stage of the disease at time of diagnosis and shortage of donors. Therefore, several minimally invasive image-guided therapies for locoregional tre...

Multiple problems, including high computational cost, spurious local minima, and solutions with no geologic sense, have prevented widespread application of full waveform inversion (FWI), especially FWI of seismic reflections. These problems are fundamentally related to a large number of model parameters and to the absence of low frequencies in recorded seismograms. Instead of inverting for all ...

Nous pr esentons un algorithme de segmentation multi-canaux qui est d eduit de la fonctionnelle de Mumford et Shah. La m ethode est un algorithme de croissance sur une image \vectorielle". Les applications pr esent ees sont la discrimination de textures et la d etection d'objets sur fond naturel.

Perceptual watermarking should take full advantage of the results from human visual system (HVS) studies. Just noticeable distortion (JND) gives us a way to model the HVS accurately. In this paper, another very important aspect affecting human perception, visual saliency, is introduced to modulate JND model. Based on the visual saliency’s modulatory effect on JND model which incorporates visual...

Diagnostic and therapeutic CT- guided percutaneous interventions are clinical routine in interventional radiology. Image-guided navigation systems visualize the internal anatomy during interventions in real time not necessitating continuous image acquisition. Although multiple 3D image-guidance devices have been developed and used by several surgical disciplines in the last few years, they have...

Recently, various image-to-image translation (I2I) methods have improved mode diversity and visual quality in terms of neural networks or regularization terms. However, conventional I2I relies on a static decision boundary the encoded representations those are entangled with each other, so they often face ‘mode collapse’ phenomenon. To mitigate collapse, 1) we design so-called style-guided disc...