This paper deals with the resolution of inverse problems in a periodic setting or, in other
terms, the reconstruction of periodic continuous-domain signals from their noisy …

In past two decades, the automation of industrial machines is proliferating. Fourth industrial
revolution (Industry 4.0) also focuses on industrial automation and artificial intelligence. As …

We provide a generic framework to learn shape dictionaries of landmark-based curves that
are defined in the continuous domain. We first present an unbiased alignment method that …

Existing shape models with spherical topology are typically designed either in the discrete
domain using interpolating polygon meshes or in the continuous domain using smooth but …

An energy efficient truncated inner product unit is proposed in this paper. The proposed unit
is pipelined and processes the m pairs of n-bit operands in serial, so that only one unit is …

This paper proposes an inner product unit with energy and area efficiency by optimizing
computation overhead. To reduce computation costs, we restructure the order of inner …

In past two decades, the automation of industrial machines is proliferating. The fourth
industrial revolution (Industry 4.0) also focuses on industrial automation and artificial …

We propose a new formulation of the active surface model in 3D. Instead of aligning a shape
dictionary through the similarity transform, we consider more flexible affine transformations …

Ongoing advances in imaging techniques create new demands regarding the analysis of
images in medicine and biology. Image segmentation is a key step of many image analysis …

In this thesis, we present a novel generic and unifying framework for data-adaptive shape
modeling. Our work is motivated by the raising need for powerful geometric modeling …