Multi-scale Improves Boundary Detection in Natural Images

Authors:
Xiaofeng Ren
Affiliations:
Toyota Technological Institute at Chicago, Chicago, USA IL 60637
Venue:
ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part III
Year:
2008

Citing 0
Cited 11

Boundary detection using f-measure-, filter- and feature- (F3) boost

ECCV'10 Proceedings of the 11th European conference on Computer vision: Part II
Finding semantic structures in image hierarchies using Laplacian graph energy

ECCV'10 Proceedings of the 11th European conference on Computer vision: Part IV
An efficient color image segmentation algorithm using hybrid approaches

Proceedings of the Seventh Indian Conference on Computer Vision, Graphics and Image Processing
Color texture image segmentation based on neutrosophic set and wavelet transformation

Computer Vision and Image Understanding
Computational-geometry approach to digital image contour extraction

Transactions on computational science XIII
Globally optimal image partitioning by multicuts

EMMCVPR'11 Proceedings of the 8th international conference on Energy minimization methods in computer vision and pattern recognition
A particle filter framework for contour detection

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part I
Efficient closed-form solution to generalized boundary detection

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part IV
Contour detection model with multi-scale integration based on non-classical receptive field

Neurocomputing
SLEDGE: Sequential Labeling of Image Edges for Boundary Detection

International Journal of Computer Vision
A combined post-filtering method to improve accuracy of variational optical flow estimation

Pattern Recognition

Quantified Score

Hi-index	0.02

Visualization

Abstract

In this work we empirically study the multi-scale boundary detection problem in natural images. We utilize local boundary cues including contrast, localization and relative contrast, and train a classifier to integrate them across scales. Our approach successfully combines strengths from both large-scale detection (robust but poor localization) and small-scale detection (detail-preserving but sensitive to clutter). We carry out quantitative evaluations on a variety of boundary and object datasets with human-marked groundtruth. We show that multi-scale boundary detection offers large improvements, ranging from 20% to 50%, over single-scale approaches. This is the first time that multi-scale is demonstrated to improve boundary detection on large datasets of natural images.