We propose a novel automatic salient object segmentation algorithm which integrates both bottom-up salient stimuli and object-level shape prior, i.e., a salient object has a well-defined closed boundary. Our approach is formalized as iterative energy minimization framework, leading to binary segmentation of the salient object. Such energy minimization is initialized with saliency map which is c...

We propose a robust interpolation for multigrid based on the concepts of energy minimization and approximation. The formulation is general; it can be applied to any dimensions. The analysis for one dimension proves that the convergence rate of the resulting multigrid method is independent of the coeecient of the underlying PDE, in addition to being independent of the mesh size. We demonstrate n...

The inference capabilities of humans suggest that they might be using algorithms with high degrees of parallelism. This paper develops a completely parallel connectionist inference mechanism. The mechanism handles obvious inferences, where each clause is only used once, but may be extendable to harder cases. The main contribution of this paper is to show formally that some inference can be redu...

Thin-walled structures like crash boxes may be used as energy absorption members in automotive chassis. There have been many studies addressing the behaviors of energy absorption members on frontal crash. These researches have attempted to predict the energy absorption and maximum impact load in shell structures. The energy absorption and maximum impact load depend on many parameters including ...

This paper studies the task of inferring a binary vector s given noisy observations of the binary vector t = As modulo 2, where A is an M N binary matrix. This task arises in correlation attack on a class of stream ciphers and in the decoding of error correcting codes. The unknown binary vector is replaced by a real vector of probabilities that are optimized by variational free energy minimizat...

Recently, there has been increasing interest in Markov random eld (MRF) modeling for solving a variety of computer vision problems formulated in terms of the maximum a posteriori (MAP) probability. When the label set is discrete, such as in image segmentation and matching, the minimization is combinatorial. The objective of this paper is twofold: Firstly, we propose to use the continuous relaxa...

We present a three-dimensional computational study of whole-cell equilibrium shape and deformation of human red blood cell (RBC) using spectrin-level energetics. Random network models consisting of degree-2, 3, ..., 9 junction complexes and spectrin links are used to populate spherical and biconcave surfaces and intermediate shapes, and coarse-grained molecular dynamics simulations are then per...

Inspired by recent results on self-avoiding inextensible curves, we propose and experimentally investigate a numerical method for simulating isometric plate bending without self-intersections. We consider nonlinear two-dimensional Kirchhoff model which is augmented via addition of tangent-point energy. The resulting continuous energy finite if only the corresponding deformation injective, i.e.,...

This paper presents an analysis on energy consumption and energy efficiency of a hexapod robot during its turning motion over flat terrain. The energy consumption model has been derived for statically stable wave-turning gaits by considering a minimization of dissipating energy for optimal foot force distribution. Two approaches, such as minimization of norm of feet forces and minimization of n...

This thesis investigates the employment of different deformable registration techniques to register pre-operative magnetic resonance and inter-operative ultrasound images during prostate biopsy. Accurate registration ensures appropriate biopsy sampling of malignant prostate tissues and reduces the rate of re-biopsies. Therefore, we provide comparisons and experimental results for some landmarka...