Open AccessProceedings Article
Segmentation Circuits Using Constrained Optimization
John G. Harris
- 02 Dec 1991
- Vol. 4, pp 797-804
TL;DR: A novel segmentation algorithm has been developed utilizing an absolute-value smoothness penalty instead of the more common quadratic regularizer, which imposes a piece-wise constant constraint on the segmented data.
read more
Abstract: A novel segmentation algorithm has been developed utilizing an absolute-value smoothness penalty instead of the more common quadratic regularizer. This functional imposes a piece-wise constant constraint on the segmented data. Since the minimized energy is guaranteed to be convex, there are no problems with local minima and no complex continuation methods are necessary to find the unique global minimum. By interpreting the minimized energy as the generalized power of a nonlinear resistive network, a continuous-time analog segmentation circuit was constructed.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Ill-posed problems in early vision: from computational theory to analogue networks
Tomaso Poggio,Christof Koch +1 more
TL;DR: A theoretical framework is outlined that leads from the computational nature of early vision to algorithms for solving them and finally to a specific class of analogue and parallel hardware for the efficient solution of these algorithms.
125
References
Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images
Stuart Geman,Donald Geman +1 more
TL;DR: The analogy between images and statistical mechanics systems is made and the analogous operation under the posterior distribution yields the maximum a posteriori (MAP) estimate of the image given the degraded observations, creating a highly parallel ``relaxation'' algorithm for MAP estimation.
•Book
Analog VLSI and Neural Systems
Carver A. Mead
- 01 Jan 1989
TL;DR: This chapter discusses a simple circuit that can generate a sinusoidal response and calls this circuit the second-order section, which can be used to generate any response that can be represented by two poles in the complex plane, where the two poles have both real and imaginary parts.
2.8K
Ill-posed problems in early vision
Mario Bertero,Tomaso Poggio,Vincent Torre +2 more
- 01 Aug 1988
TL;DR: In this article, the authors reviewed mathematical results on ill-posed and ill-conditioned problems and formal aspects of regularization theory in the linear case are introduced, characterizing existence, uniqueness, and stability of solutions.
Analog "neuronal" networks in early vision
TL;DR: This work illustrates this approach by implementing a specific analog network, solving the problem of reconstructing a smooth surface from sparse data while preserving its discontinuities, and suggests a novel computational strategy for solving early vision problems in both biological and real-time artificial vision systems.
332
Ill-Posed Problems in Early Vision: From Computational Theory to Analogue Networks
Tomaso Poggio,Christof Koch +1 more
TL;DR: A theoretical framework is outlined that leads from the computational nature of early vision to algorithms for solving them and finally to a specific class of analogue and parallel hardware for the efficient solution of these algorithms.