Computational analysis and learning for a biologically motivated model of boundary detection

Authors:
Iasonas Kokkinos;Rachid Deriche;Olivier Faugeras;Petros Maragos
Affiliations:
School of Electrical and Computer Engineering, National Technical University of Athens, Athens, Greece;Institut National de Recherche en Informatique et Automatique, Sophia-Antipolis, France;Institut National de Recherche en Informatique et Automatique, Sophia-Antipolis, France;School of Electrical and Computer Engineering, National Technical University of Athens, Athens, Greece
Venue:
Neurocomputing
Year:
2008

Citing 31
Cited 4

A Computational Approach to Edge Detection

IEEE Transactions on Pattern Analysis and Machine Intelligence
Neural dynamics of surface perception: boundary webs, illuminants, and shape-from-shading

Computer Vision, Graphics, and Image Processing
Trace Inference, Curvature Consistency, and Curve Detection

IEEE Transactions on Pattern Analysis and Machine Intelligence
Scale-Space and Edge Detection Using Anisotropic Diffusion

IEEE Transactions on Pattern Analysis and Machine Intelligence
Introduction to the theory of neural computation

Introduction to the theory of neural computation
Learning and relearning in Boltzmann machines

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
A common framework for image segmentation

International Journal of Computer Vision
Variational methods in image segmentation

Variational methods in image segmentation
Deterministic learning rules for Boltzmann machines

Neural Networks
Synthetic aperture radar processing by a multiple scale neural system for boundary and surface representation

Neural Networks - Special issue: automatic target recognition
A maximum entropy approach to natural language processing

Computational Linguistics
Inferring global perceptual contours from local features

International Journal of Computer Vision - Special issue on computer vision research at the University of Southern California
Stochastic completion fields: a neural model of illusory contour shape and salience

Neural Computation
Visual cortical mechanisms of perceptual grouping: interacting layers, networks, columns, and maps

Neural Networks
Learning Low-Level Vision

International Journal of Computer Vision - Special issue on statistical and computational theories of vision: modeling, learning, sampling and computing, Part I
Neural Networks and Natural Intelligence

Neural Networks and Natural Intelligence
Statistical Edge Detection: Learning and Evaluating Edge Cues

IEEE Transactions on Pattern Analysis and Machine Intelligence
Texture Segmentation by Minimizing Vector-Valued Energy Functionals: The Coupled-Membrane Model

ECCV '92 Proceedings of the Second European Conference on Computer Vision
A Probabilistic Multi-scale Model for Contour Completion Based on Image Statistics

ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part I
Sketches with Curvature: The Curve Indicator Random Field and Markov Processes

IEEE Transactions on Pattern Analysis and Machine Intelligence
Region competition: unifying snakes, region growing, energy/Bayes/MDL for multi-band image segmentation

ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
Energy Functions for Early Vision and Analog Networks

Energy Functions for Early Vision and Analog Networks
Learning to Detect Natural Image Boundaries Using Local Brightness, Color, and Texture Cues

IEEE Transactions on Pattern Analysis and Machine Intelligence
Fields of Experts: A Framework for Learning Image Priors

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
Biophysics of Computation: Information Processing in Single Neurons (Computational Neuroscience Series)

Biophysics of Computation: Information Processing in Single Neurons (Computational Neuroscience Series)
Supervised Learning of Edges and Object Boundaries

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
Theoretical Neuroscience: Computational and Mathematical Modeling of Neural Systems

Theoretical Neuroscience: Computational and Mathematical Modeling of Neural Systems
Supervised tensor learning

Knowledge and Information Systems
General Tensor Discriminant Analysis and Gabor Features for Gait Recognition

IEEE Transactions on Pattern Analysis and Machine Intelligence
Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images

IEEE Transactions on Pattern Analysis and Machine Intelligence
Robust anisotropic diffusion

IEEE Transactions on Image Processing

Computer Vision: A Plea for a Constructivist View

AIME '09 Proceedings of the 12th Conference on Artificial Intelligence in Medicine: Artificial Intelligence in Medicine
Spatially-variant structuring elements inspired by the neurogeometry of the visual cortex

ISMM'11 Proceedings of the 10th international conference on Mathematical morphology and its applications to image and signal processing
Color-texture image segmentation and recognition through a biologically-inspired architecture

Pattern Recognition and Image Analysis
Learning to resize image

Neurocomputing

Quantified Score

Hi-index	0.01

Visualization

Abstract

In this work we address the problem of boundary detection by combining ideas and approaches from biological and computational vision. Initially, we propose a simple and efficient architecture that is inspired from models of biological vision. Subsequently, we interpret and learn the system using computer vision techniques: First, we present analogies between the system components and computer vision techniques and interpret the network as minimizing a cost functional, thereby establishing a link with variational techniques. Second, based on Mean Field Theory the equations describing the network behavior are interpreted statistically. Third, we build on this interpretation to develop an algorithm to learn the network weights from manually segmented natural images. Using a systematic evaluation on the Berkeley benchmark we show that when using the learned connection weights our network outperforms classical edge detection algorithms.