no code implementations • 20 Nov 2023 • Xuechao Wang, Junqing Huang, Sven Nomm, Marianna Chatzakou, Kadri Medijainen, Aaro Toomela, Michael Ruzhansky
Conclusions: We present a series of experiments with extensive analysis, which systematically demonstrate the effectiveness and efficiency of the proposed hybrid neural network in extracting distinctive handwriting patterns for precise diagnosis of Parkinson's disease.
no code implementations • 3 Nov 2023 • Junqing Huang, Haihui Wang, Andreas Weiermann, Michael Ruzhansky
In this paper, we derive a novel optimal image transport algorithm over sparse dictionaries by taking advantage of Sparse Representation (SR) and Optimal Transport (OT).
no code implementations • 17 Aug 2023 • Junqing Huang, Haihui Wang, Michael Ruzhansky
Image structure-texture decomposition is a long-standing and fundamental problem in both image processing and computer vision fields.
no code implementations • 2 Feb 2023 • Xuechao Wang, Junqing Huang, Marianna Chatzakou, Kadri Medijainen, Pille Taba, Aaro Toomela, Sven Nomm, Michael Ruzhansky
In recent years, deep learning methods have achieved great success in various fields due to their strong performance in practical applications.
1 code implementation • 1 Jul 2021 • Junqing Huang, Michael Ruzhansky, Qianying Zhang, Haihui Wang
We illustrate that all losses can be reduced without the necessity of taking an intrinsic image decomposition under the well-known spatial-varying illumination illumination-invariant reflectance prior knowledge.
1 code implementation • 1 Jul 2021 • Junqing Huang, Haihui Wang, Xuechao Wang, Michael Ruzhansky
In this paper, we propose an interesting semi-sparsity smoothing algorithm based on a novel sparsity-inducing optimization framework.