scispace - formally typeset
Search or ask a question

Showing papers by "Stan Z. Li published in 1997"


Journal ArticleDOI
TL;DR: The extensive exploration of the curve shape constraints in both the matching and the pose estimation stages are shown to significantly improve the quality of the recognition and pose estimation of 3D space curves.

27 citations


Journal ArticleDOI
TL;DR: This paper proposes to use the continuous relaxation labeling (RL) as an alternative approach for the minimization, and compares various algorithms proposed, namely, the RL algorithms proposed by Rosenfeld et al., and by Hummel and Zucker.
Abstract: Recently, there has been increasing interest in Markov random field (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 relaxation labeling (RL) as an alternative approach for the minimization. The motivation is that it provides a good compromise between the solution quality and the computational cost. We show how the original combinatorial optimization can be converted into a form suitable for continuous RL. Secondly, we compare various minimization algorithms, namely, the RL algorithms proposed by Rosenfeld et al., and by Hummel and Zucker, the mean field annealing of Peterson and Soderberg, simulated annealing of Kirkpatrick, the iterative conditional modes (ICM) of Besag and an annealing version of ICM proposed in this paper. The comparisons are in terms of the minimized energy value (i.e., the solution quality), the required number of iterations (i.e., the computational cost), and also the dependence of each algorithm on heuristics.

22 citations


Journal ArticleDOI
TL;DR: A novel theory of parameter estimation for optimization-based object recognition where the optimal solution is defined as the global minimum of an energy function.
Abstract: Object recognition systems involve parameters such as thresholds, bounds and weights. These parameters have to be tuned before the system can perform successfully. A common practice is to choose such parameters manually on an {\it add\ hoc} basis, which is a disadvantage. This paper presents a novel theory of parameter estimation for optimization-based object recognition where the optimal solution is defined as the global minimum of an energy function. The theory is based on supervised learning from examples. {\it Correctness} and {\it instability} are established as criteria for evaluating the estimated parameters. A correct estimate enables the labeling implied in each exemplary configuration to be encoded in a unique global energy minimum. The instability is the ease with which the minimum is replaced by a non-exemplary configuration after a perturbation. The optimal estimate minimizes the instability. Algorithms are presented for computing correct and minimal-instability estimates. The theory is applied to the parameter estimation for MRF-based recognition and promising results are obtained.

17 citations


Book ChapterDOI
21 May 1997
TL;DR: This paper presents an iterative optimization algorithm, called the Comb algorithm, for approximating the global minmum, and shows that the Comb produces solutions of quality much better than ICM and comparable to simulated annealing.
Abstract: The maximum a posteriori (MAP) principle is often used in image restoration and segmentation to define the optimal solution when both the prior and likelihood distributions are available MAP estimation is equivalent to minimizing an energy function It is desirable to find the global minimum However, the minimization in the MAP image estimation is non-trivial due to the use of contextual constraints between pixels Steepest descent methods such as ICM quickly finds a local minimum but the solution quality depends much on the initialization Some initializations are better than others In this paper, we present an iterative optimization algorithm, called the Comb algorithm, for approximating the global minmum The Comb maintains a number of best local minima found so far It uses the Common structure of Best local minima (hence “Comb”) to derive new initial configurations Because the derived configurations contain some structure resembling that of the global minimum, they may provide good starting points for local search to approach the global minimum Experimental comparisons show that the Comb produces solutions of quality much better than ICM and comparable to simulated annealing

7 citations


Journal Article
TL;DR: The modified hemispherectomy showed total control of seizures in 28 children with chronic epilepsy or near-total control in the others, and marked shift of the remaining hemisphere on brain-stem auditory evoked potentials.
Abstract: To overcome long-term complications of hemispherectomy, We modified its operative method. The modified hemispherectomy was performed for 31 patients between 1985 and 1992. These patients were studied for 7 years after operation. The results showed total control of seizures in 28 children with chronic epilepsy (90%) or near-total control in the others. No deaths or delayed complications were noted but improvement in behavior and hemiplegia. CT and MRI showed marked shift of the remaining hemisphere. On brain-stem auditory evoked potentials, the latency of peak I was not variant (P > 0.05). The method makes the insulation of the subdural cavity from the ventricular system more reliable, and climates the pathological conditions.

2 citations