Results 1 
5 of
5
Globallocal optimizations by hierarchical cuts and climbing energies
, 2013
"... Hierarchical segmentation is a multiscale analysis of an image and provides a series of simplifying nested partitions. Such a hierarchy is rarely an end by itself and requires external criteria or heuristics to solve problems of image segmentation, texture extraction and semantic image labelling. I ..."
Abstract

Cited by 4 (2 self)
 Add to MetaCart
(Show Context)
Hierarchical segmentation is a multiscale analysis of an image and provides a series of simplifying nested partitions. Such a hierarchy is rarely an end by itself and requires external criteria or heuristics to solve problems of image segmentation, texture extraction and semantic image labelling. In this theoretical paper we introduce a novel framework: hierarchical cuts, to formulate optimization problems on hierarchies of segmentations. Second we provide the three important notions of hincreasing, singular, and scale increasing energies, necessary to solve the global combinatorial optimization problem of partition selection and which results in linear time dynamic programs. Common families of such energies are summarized, and also a method to generate new ones is described. Finally we demonstrate the application of this framework on problems of image segmentation and texture enhancement.
F.: Supervised assessment of segmentation hierarchies
 In: Computer Vision  ECCV 2012. Volume 7575 of LNCS. (2012) 814–827
"... Abstract. This paper addresses the problem of the supervised assessment of hierarchical regionbased image representations. Given the large amount of partitions represented in such structures, the supervised assessment approaches in the literature are based on selecting a reduced set of representa ..."
Abstract

Cited by 4 (1 self)
 Add to MetaCart
(Show Context)
Abstract. This paper addresses the problem of the supervised assessment of hierarchical regionbased image representations. Given the large amount of partitions represented in such structures, the supervised assessment approaches in the literature are based on selecting a reduced set of representative partitions and evaluating their quality. Assessment results, therefore, depend on the partition selection strategy used. Instead, we propose to find the partition in the tree that best matches the groundtruth partition, that is, the upperbound partition selection. We show that different partition selection algorithms can lead to different conclusions regarding the quality of the assessed trees and that the upperbound partition selection provides the following advantages: 1) it does not limit the assessment to a reduced set of partitions, and 2) it better discriminates the random trees from actual ones, which reflects a better qualitative behavior. We model the problem as a Linear Fractional Combinatorial Optimization (LFCO) problem, which makes the upperbound selection feasible and efficient. 1
A contrario edge detection with edgelets
"... Abstract—Edge detection remains an active problem in the image processing community, because of the high complexity of natural images. In the last decade, Desolneux et al. proposed a novel detection approach, parameter free, based on the Helmhotz principle. Applied to the edge detection field, this ..."
Abstract

Cited by 2 (1 self)
 Add to MetaCart
(Show Context)
Abstract—Edge detection remains an active problem in the image processing community, because of the high complexity of natural images. In the last decade, Desolneux et al. proposed a novel detection approach, parameter free, based on the Helmhotz principle. Applied to the edge detection field, this means that observing a true edge in random and independent conditions is very unlikely, and then considered as meaningful. However, overdetection may occur, partly due to the use of a single pixelwise feature. In this paper, we propose to introduce higher level information in the a contrario framework, by computing several features along a set of connected pixels (an edgelet). Among the features, we introduce a shape prior, learned on a database. We propose to estimate online the a contrario distributions of the two other features, namely the gradient and the texture, by a MonteCarlo simulation approach. Experiments show that our method improves the original one, by decreasing the number of non relevant edges while preserving the true ones. I.
Climbing: A Unified Approach for Global Constraints on Hierarchical Segmentation
"... Abstract. The paper deals with global constraints for hierarchical segmentations. The proposed framework associates, with an input image, a hierarchy of segmentations and an energy, and the subsequent optimization problem. It is the first paper that compiles the different global constraints and unif ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
(Show Context)
Abstract. The paper deals with global constraints for hierarchical segmentations. The proposed framework associates, with an input image, a hierarchy of segmentations and an energy, and the subsequent optimization problem. It is the first paper that compiles the different global constraints and unifies them as Climbing energies. The transition from global optimization to local optimization is attained by the hincreasingness property, which allows to compare parent and child partition energies in hierarchies. The laws of composition of such energies are established and examples are given over the Berkeley Dataset for colour and texture segmentation. 1
Optima on Hierarchies of Partitions
 ISMM 2013, UPPSALA: SWEDEN
, 2013
"... A new approach is proposed for finding optimal cuts in hierarchies of partitions by energy minimization. It rests on the notion of hincreasingness, allows to find best(optimal) cuts in one pass, and to obtain nice ”climbing ” scale space operators. The ways to construct hincreasing energies, and t ..."
Abstract
 Add to MetaCart
A new approach is proposed for finding optimal cuts in hierarchies of partitions by energy minimization. It rests on the notion of hincreasingness, allows to find best(optimal) cuts in one pass, and to obtain nice ”climbing ” scale space operators. The ways to construct hincreasing energies, and to combine them are studied, and illustrated by two examples on color and on textures.