HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information
Skip to Main content Skip to Navigation

Towards bridging the Gap between Biological and Computational Image Segmentation

Iasonas Kokkinos 1 Rachid Deriche 2 Théodore Papadopoulo 2, * Olivier Faugeras 2 Petros Maragos 1
* Corresponding author
2 ODYSSEE - Computer and biological vision
DI-ENS - Département d'informatique - ENS Paris, CRISAM - Inria Sophia Antipolis - Méditerranée , ENS-PSL - École normale supérieure - Paris, Inria Paris-Rocquencourt, ENPC - École des Ponts ParisTech
Abstract : This report presents a joint study of biological and computational vision. First we briefly review the most common models of neurons and neural networks and the function of cells in the V1/V2 areas of the visual cortex. Subsequently, we present the biologically plausible models for image segmentation that have been proposed by Stephen Grossberg and his collaborators during the previous two decades in a series of papers. We have implemented the B.C.S. (Boundary Contour System) and F.C.S. (Feature Contour System) models that form the basic building blocks of this model of biological vision, known as FACADE (Form And Colour and DEpth) theory. During their implementation, we faced several problems, like a large number of parameters and instability with respect to these; this was not traded off with a higher performance when compared to classical computer vision algorithms. This has led us to propose a simplified version of the B.C.S./F.C.S. system, and to explore the merits of using nonlinear recurrent dynamics. The biologically plausible model we propose is paralleled with classical computational vision techniques, while a link with the variational approach to computer vision is established. By interpreting the network's function in a probabilistic manner we derive an algorithm for learning the network weights using manually determined segmentations excerpted from the Berkeley database. This facilitates learning the terms involved in the variational criterion that quantifies edge map quality from ground truth data. Using the learned weights our network outperforms classical edge detection algorithms, when evaluated on the Berkeley segmentation benchmark.
Complete list of metadata

Cited literature [75 references]  Display  Hide  Download

Contributor : Théodore Papadopoulo Connect in order to contact the contributor
Submitted on : Monday, October 8, 2007 - 2:32:15 PM
Last modification on : Thursday, March 17, 2022 - 10:08:30 AM
Long-term archiving on: : Friday, November 25, 2016 - 6:28:23 PM


Files produced by the author(s)


  • HAL Id : inria-00176890, version 2


Iasonas Kokkinos, Rachid Deriche, Théodore Papadopoulo, Olivier Faugeras, Petros Maragos. Towards bridging the Gap between Biological and Computational Image Segmentation. [Research Report] RR-6317, INRIA. 2007, pp.111. ⟨inria-00176890v2⟩



Record views


Files downloads