Analysis of Keywords used in Image Understanding Tasks (2009)
In the field of computer vision, automated image annotation and object recognition are currently important research topics. It is hoped that these will lead to improved general image understanding...
A Survey of Methods for Image Annotation ⋆ (2009)
In order to evaluate automated image annotation and object recognition algorithms, ground truth in the form of a set of images correctly annotated with text describ-ing each image is required. In...
A Study of Vocabularies for Image Annotation (2009)
Abstract. In order to evaluate image annotation and object categorisation algorithms, ground truth in the form of a set of images correctly annotated with text describing each image is required....
How Do Superpixels Affect Image Segmentation? (2009)
Abstract. Computationally intensive segmentation algorithms often operate on an image pre-segmented into small regions referred to as “superpixels”. We investigate the effect of the choice of the...
The Morphological Top-Hat Operator Generalised to Multi-channel Images (2009)
The morphological top-hat operator for greyscale images is part of the basic toolbox of mathematical morphology operators. We discuss two ways of generalising the tophat operator to multi-channel...
Czech Pattern Recognition Society Texture segmentation through salient texture patches (2009)
A novel approach to automatic, hierarchical texture detection in single images as a step towards image understanding is presented. First, the proposed method searches for alternating color patterns...
ILLUMINATION-INVARIANT MORPHOLOGICAL TEXTURE CLASSIFICATION (2009)
Allan Hanbury, Umasankar K, Donald A. Adjeroh
Abstract We investigate the use of the standard morphological texture characterisation methods, the granulometry and the variogram, in the task of texture classification. These methods are applied to...
Problems with Running a Successful Multimedia Retrieval Benchmark ∗ (2009)
Henning Müller, Thomas Deselaers, Michael Grubinger, Paul Clough, Allan Hanbury, William Hersh
Content-based image retrieval (CBIR) and multimedia retrieval are at the point where they are ready to leave the pure research status and become integrated into commercial prototypes and products....
Motion Detection Using an Improved Colour Model ⋆ (2009)
Horst Wildenauer, Allan Hanbury, Martin Kampel
Abstract. We discuss common colour models for background subtraction and problems related to their utilisation. A novel approach to represent chrominance information more suitable for robust...
Horst Wildenauer, Allan Hanbury, Martin Kampel
Abstract In this paper, common colour models for background subtraction and problems related to their utilisation are discussed. A novel approach to represent chrominance information more suitable...
Evaluation of Gradient Vector Flow for Interest Point Detection (2009)
Julian Stöttinger, René Donner, Lech Szumilas, Allan Hanbury
Abstract. We present and evaluate an approach for finding local interest points in images based on the non-minima suppression of Gradient Vector Flow (GVF) magnitude. Based on the GVF’s properties...
Constructing Cylindrical Coordinate Colour Spaces (2009)
A cylindrical coordinate colour space (lightness, saturation/chroma, hue) is derived from an opponent colour space in the RGB space. It is shown how cylindrical coordinate colour models widely used...
The MUSCLE Live Image Retrieval Evaluation Event ∗ (2009)
Allan Hanbury, Julian Stöttinger
This paper presents an overview of the live image retrieval evaluation event held at the CIVR 2007. It describes the organisation of the event and the dataset used, lists the queries used, and...
Colour Adjacency Histograms for Image Matching (2009)
Allan Hanbury, Beatriz Marcotegui
Abstract. The use of 2D colour adjacency histograms for image matching in image retrieval scenarios is investigated. We present an algorithm for extracting representative colours from an image and a...
Waterfall Segmentation of Complex Scenes ⋆ (2009)
Allan Hanbury, Beatriz Marcotegui
Abstract. We present an image segmentation technique using the morphological Waterfall algorithm. Improvements in the segmentation are brought about by using improved gradients. These are based on...
Radial Edge Configuration for Semi-local Image Structure Description (2009)
Lech Szumilas, Horst Wildenauer, Allan Hanbury, René Donner
Abstract. We present a novel semi-local image descriptor which encodes multiple edges corresponding to the image structure boundaries around an interest point. The proposed method addresses the...
Morphological Distinguished Regions ⋆ (2009)
Abstract. Distinguished regions can be detected with high repeatability in different images of the same scene. Two definitions of distinguished regions of an image in a mathematical morphology...
Color Pair Clustering for Texture Detection ⋆ (2009)
Abstract. A novel approach to the extraction of image regions of uniform color and its application to automatic texture detection is discussed. The method searches for alternating color patterns,...
The Visual Concept Detection Task in (2009)
Thomas Deselaers, Allan Hanbury
The Visual Concept Detection Task (VCDT) of ImageCLEF 2008 is described. A database of 2,827 images were manually annotated with 17 concepts. Of these, 1,827 were used for training and 1,000 for...
Radial Edge Configuration for Semi-Local Image Structure Description (2008)
Lech Szumilas, Horst Wildenauer, Allan Hanbury, Rene Donner
We present a novel semi-local image descriptor which encodes multiple edges corresponding to the image structure boundaries around an interest point. The proposed method addresses the problem of poor...
A Dataset of Annotated Animals ∗ (2008)
Allan Hanbury, Alireza Tavakoli Targhi
An annotation of 59 795 images from the Corel database is presented. Each image has been labelled as containing an animal or not. The type of animal is also specified for most images. In addition,...
Improved motion segmentation based on shadow detection (2008)
Martin Kampel, Allan Hanbury, Philipp Blauensteiner, Horst Wildenauer
Improved motion segmentation based on shadow detection (2008)
Martin Kampel, Allan Hanbury, Philipp Blauensteiner, Horst Wildenauer
MATHEMATICAL MORPHOLOGY IN THE CIELAB SPACE (2008)
The use of mathematical morphology in the CIE L*a*b * colour space is discussed. It is possible to impose a total order on the colour vectors in this space by using a weighting function and...
Template patch driven image segmentation ∗ (2008)
We present a method that partitions a single image into two layers, requiring that one layer has similar properties in terms of pixel colour variation to a provided template patch. First, the paper...
Color Pair Clustering for Texture Detection ⋆ (2008)
Abstract. A novel approach to the extraction of image regions of uniform color and its application to automatic texture detection is discussed. The method searches for alternating color patterns,...
Czech Pattern Recognition Society Extraction of Attributes, Nature and Context of Images (2008)
Abstract In this paper a framework for deriving highlevel scene attributes from low-level image features is presented. Examples of attributes derived are photo-painting, indoor-outdoor, night-day and...
Overview of the ImageCLEF 2007 Object Retrieval Task (2008)
Deselaers, Thomas, Hanbury, Allan, Viitaniemi, Ville, Farquhar, Jason D.R., Brendel, Mátyás, Daróczy, Bálint, ...
We describe the object retrieval task of ImageCLEF 2007, give an overview of the methods of the participating groups, and present and discuss the results. The task was based on the widely used PASCAL...
We present image segmentation and highlight detection algorithms based on the dichromatic reflection model. For image segmentation, we use the model prediction that objects of a certain colour...
Overview of the ImageCLEF 2007 Object Retrieval Task (2007)
Deselaers, Thomas, Hanbury, Allan, Viitaniemi, Ville, Benczur, Andras, Brendel, Matyas, Daroczy, Balint, ...
We describe the object retrieval task of ImageCLEF 2007, give an overview of the methods of the participating groups, and present and discuss the results. The task was based on the widely used PASCAL...
Overview of the ImageCLEFphoto 2007 photographic retrieval task (2007)
Michael Grubinger, Paul Clough, Allan Hanbury, Henning Müller
ImageCLEFphoto 2007 is the general photographic ad-hoc retrieval task of the Image-CLEF 2007 evaluation campaign and provides both the resources and the framework necessary to perform comparative...
Overview of the ImageCLEFphoto 2007 photographic retrieval task (2007)
Michael Grubinger, Allan Hanbury, Henning Müller
Abstract. The general photographic ad-hoc retrieval task of the ImageCLEF 2007 evaluation campaign is described. This task provides both the resources and the framework necessary to perform...
Overview of the ImageCLEF 2007 object retrieval task (2007)
Thomas Deselaers, Allan Hanbury, Ville Viitaniemi, András Benczúr, Mátyás Brendel, Bálint Daróczy, ...
Abstract. We describe the object retrieval task of ImageCLEF 2007, give an overview of the methods of the participating groups, and present and discuss the results. The task was based on the widely...
A.: Local structure detection with orientation-invariant radial configuration (2007)
Lech Szumilas, René Donner, Georg Langs, Allan Hanbury
Local image descriptors have proved themselves as useful tools for many computer vision tasks such as matching points between multiple images of a scene and object recognition. Current descriptors,...
Improved motion segmentation based on shadow detection (2006)
Kampel, Martin, Hanbury, Allan, Blauensteiner, Philipp, Wildenauer, Horst
Automatic image segmentation by positioning a seed (2006)
Abstract. We present a method that automatically partitions a single image into non-overlapping regions coherent in texture and colour. An assumption that each textured or coloured region can be...
H.: Overview of the ImageCLEF 2006 photographic retrieval and object annotation tasks (2006)
Paul Clough, Michael Grubinger, Thomas Deselaers, Allan Hanbury, Henning Müller
This paper describes the general photographic retrieval and object annotation tasks of the ImageCLEF 2006 evaluation campaign. These tasks provide both the resources and the framework necessary to...
Review of Image Annotation for the Evaluation of Computer Vision Algorithms (2006)
In the field of computer vision, automated image annotation and object recognition are currently important research topics. It is hoped that these will lead to improved general image understanding...
Automatic image segmentation by positioning a seed (2006)
Abstract. We present a method that automatically partitions a single image into non-overlapping regions coherent in texture and colour. An assumption that each textured or coloured region can be...
H.: Overview of the ImageCLEF 2006 photographic retrieval and object annotation tasks (2006)
Paul Clough, Michael Grubinger, Thomas Deselaers, Allan Hanbury, Henning Müller
Abstract. This paper describes the general photographic retrieval and object annotation tasks of the ImageCLEF 2006 evaluation campaign. These tasks provided both the resources and the framework...
Results of the muscle cis coin competition 2006 (2006)
Michael Nölle, Michael Rubik, Allan Hanbury
We present the history and structure of the MUSCLE Coin Images Seibersdorf (CIS) benchmark, as well as the results of the CIS coin recognition competition 2006. 1
B.: Waterfall segmentation of complex scenes (2006)
Allan Hanbury, Beatriz Marcotegui
Abstract. We present an image segmentation technique using the morphological Waterfall algorithm. Improvements in the segmentation are brought about by using improved gradients. These are based on...
Automatic image segmentation by positioning a seed (2006)
Abstract. We present a method that automatically partitions a single image into non-overlapping regions coherent in texture and colour. An assumption that each textured or coloured region can be...
Cette thèse porte principalement sur le traitement des images numériques dans lesquelles chaque pixel encode une valeur angulaire (une valeur qui peut être visualisée comme un point sur le cercle...
A.: Supervised texture detection in images (2005)
Abstract. This paper presents a technique for texture segmentation in images. Providing a small template of a texture of interest results in the image being segmented into regions with similar...
A.: Steerable semi-automatic segmentation of textured images (2005)
This paper generalizes the interactive method for a region segmentation of grayscale images by Boykov & Jolly (ICCV 2001) to colour and textured images. Our suggested method follows the same...
Segment feature co-ocurrence based texture detection (2005)
This work on texture detection was inspired by the general problem of object recognition in two dimensional still images. One of the crucial challenges associated with the object recognition is...
Steerable semi-automatic segmentation of textured images (2005)
Abstract. This paper generalizes the interactive method for region segmentation of grayscale images based on graph cuts by Boykov & Jolly (ICCV 2001) to colour and textured images. The main...
A system for marker-less human motion estimation (2005)
Rosenhahn, Bodo, Kersting, Uwe, Smith, Andrew, Gurney, Jason, Brox, Thomas, Klette, Reinhard, ...
In this contribution we present a silhouette based human motion estimation system. The system components contain silhouette extraction based on level sets, a correspondence module, which relates...
Three-Dimensional Shape Knowledge for Joint Image Segmentation and Pose Estimation. (2005)
Rosenhahn, Bodo, Brox, Thomas, Weickert, Joachim, Kropatsch, Walter, Sablatnig, Robert, Hanbury, Allan
This paper presents the integration of 3D shape knowledge into a variational model for level set based image segmentation and tracking. Having a 3D surface model of an object that is visible in the...
The redundancy pyramid and its application to image segmentation (2004)
Allan Hanbury, Jocelyn Marchadier, Walter G. Kropatsch
Irregular pyramids organise several topological partitions which can be deduced from a partition (called the base of the pyramid) by successive unions of regions. In this paper, we introduce the...
A Visualization Tool For Comparing (2004)
Paintings And Their, Paul Kammerer, Allan Hanbury, Ernestine Zolda
This paper will present a visualization tool for comparing images of paintings. The method starts with two types of images, one showing the color surface, the other the underdrawing - the first...
The Morphological Top-Hat Operator Generalised to Multi-channel Images (2004)
The morphological top-hat operator for greyscale images is part of the basic toolbox of mathematical morphology operators. We discuss two ways of generalising the tophat operator to multi-channel...
The isophotic metric and its application to feature sensitive morphology on surfaces (2004)
Helmut Pottmann, Tibor Steiner, Michael Hofer, Christoph Haider, Allan Hanbury
Abstract. We introduce the isophotic metric, a new metric on surfaces, in which the length of a surface curve is not just dependent on the curve itself, but also on the variation of the surface...
The isophotic metric and its application to feature sensitive morphology on surfaces (2004)
Helmut Pottmann, Tibor Steiner, Michael Hofer, Christoph Haider, Allan Hanbury
Abstract. We introduce the isophotic metric, a new metric on surfaces, in which the length of a surface curve is not just dependent on the curve itself, but also on the variation of the surface...
The redundancy pyramid and its application to segmentation on an image sequence (2004)
Jocelyn Marchadier, Walter G. Kropatsch, Allan Hanbury
Abstract. Irregular pyramids organize a sequence of partitions of images in such a way that each partition is deduced from the preceding one by union of some of its regions. In this paper, we show...
A 3D-polar coordinate colour representation well adapted to image analysis (2003)
The processing and analysis of colour images has become an important area of study and application. The representation of the RGB colour space in 3D-polar coordinates (hue, saturation and brightness)...
Circular Statistics Applied to Colour Images (2003)
Allan Hanbury Prip, Allan Hanbury
Three methods for summarising the characteristics of colour images are presented. They all rely on the ability to represent colours in terms of a 3D-polar coordinate system having independent...
Colour image analysis in 3D-polar coordinates (2003)
35 rue Saint-Honoré, F-77305 Fontainebleau cedex, France. Abstract. The use of 3D-polar coordinate representations of the RGB colour space is widespread, although many of these representations, such...
Homotopic transformations of combinatorial maps (2003)
Jocelyn Marchadier, Walter G. Kropatsch, Allan Hanbury
Abstract. In this contribution, we propose the notion of homotopy for both combinatorial maps and weighted combinatorial maps. We also describe transformations that are homotopic in the defined...
Cette thèse porte principalement sur le traitement des images numériques dans lesquelles chaque pixel encode une valeur angulaire (une valeur qui peut être visualisée comme un point sur le cercle...
Cette thèse porte principalement sur le traitement des images numériques dans lesquelles chaque pixel encode une valeur angulaire (une valeur qui peut être visualisée comme un point sur le cercle...
Cette thèse porte principalement sur le traitement des images numériques dans lesquelles chaque pixel encode une valeur angulaire (une valeur qui peut être visualisée comme un point sur le cercle...
Cette thèse porte principalement sur le traitement des images numériques dans lesquelles chaque pixel encode une valeur angulaire (une valeur qui peut être visualisée comme un point sur le cercle...
Cette thèse porte principalement sur le traitement des images numériques dans lesquelles chaque pixel encode une valeur angulaire (une valeur qui peut être visualisée comme un point sur le cercle...
Cette thèse porte principalement sur le traitement des images numériques dans lesquelles chaque pixel encode une valeur angulaire (une valeur qui peut être visualisée comme un point sur le cercle...
Cette thèse porte principalement sur le traitement des images numériques dans lesquelles chaque pixel encode une valeur angulaire (une valeur qui peut être visualisée comme un point sur le cercle...
The taming of the hue, saturation and brightness colour space (2002)
The transformation of the RGB colour space to a hue, saturation and brightness colour space is essentially a conversion from a rectangular coordinate system to a cylindrical coordinate system....
Analysis of Oriented Textures Using Mathematical Morphology (2002)
Oriented textures are characterised by a dominant orientation at each point of the texture, and can be summarised by images encoding these dominant orientations. Because of the angular values in...
École Nationale, Supérieure Mines Paris, Allan Hanbury, Allan Hanbury
with applications to hues and to oriented textures THESIS presented to the
Mathematical morphology in the L*a*b* colour space (2001)
France The use of mathematical morphology in the L*a*b * colour space is discussed. Initially, a description of the characteristics of the L*a*b * space and a comparison to the HLS space are given....
Mathematical Morphology in the HLS Colour Space (2001)
Allan Hanbury And, Allan Hanbury, Jean Serra
The HLS colour space is widely used in image analysis as it is physically intuitive. As the hue component of this space is defined on the unit circle, standard greyscale image analysis operators,...