Camille Kurtz

A hierarchical knowledge-based approach for retrieving similar medical images described with semantic annotations

Computer-assisted image retrieval applications could assist radiologist interpretations by identifying similar images in large archives as a means to providing decision support. However, the semantic gap between low-level image features and their high level semantics may impair the system performances. Indeed, it can be challenging to comprehensively characterize the images using low-level imaging features to fully capture the visual appearance of diseases on images, and recently the use of semantic terms has been advocated to provide semantic descriptions of the visual contents of images. However, most of the existing image retrieval strategies do not consider the intrinsic properties of these terms during the comparison of the images beyond treating them as simple binary (presence/absence) features. We propose a new framework that includes semantic features in images and that enables retrieval of similar images in large databases based on their semantic relations. It is based on two main steps: (1) annotation of the images with semantic terms extracted from an ontology, and (2) evaluation of the similarity of image pairs by computing the similarity between the terms using the Hierarchical Semantic-Based Distance (HSBD) coupled to an ontological measure. The combination of these two steps provides a means of capturing the semantic correlations among the terms used to characterize the images that can be considered as a potential solution to deal with the semantic gap problem. We validate this approach in the context of the retrieval and the classification of 2D regions of interest (ROIs) extracted from computed tomographic (CT) images of the liver. Under this framework, retrieval accuracy of more than 0.96 was obtained on a 30-images dataset using the Normalized Discounted Cumulative Gain (NDCG) index that is a standard technique used to measure the effectiveness of information retrieval algorithms when a separate reference standard is available. Classification results of more than 95% were obtained on a 77-images dataset. For comparison purpose, the use of the Earth Movers Distance (EMD), which is an alternative distance metric that considers all the existing relations among the terms, led to results retrieval accuracy of 0.95 and classification results of 93% with a higher computational cost. The results provided by the presented framework are competitive with the state-of-the-art and emphasize the usefulness of the proposed methodology for radiology image retrieval and classification.

Tree Leaves Extraction in Natural Images: Comparative Study of Preprocessing Tools and Segmentation Methods

In this paper, we propose a comparative study of various segmentation methods applied to the extraction of tree leaves from natural images. This study follows the design of a mobile application, developed by Cerutti et al. (published in ReVeS Participation-Tree Species Classification Using Random Forests and Botanical Features. CLEF 2012), to highlight the impact of the choices made for segmentation aspects. All the tests are based on a database of 232 images of tree leaves depicted on natural background from smartphones acquisitions. We also propose to study the improvements, in terms of performance, using preprocessing tools, such as the interaction between the user and the application through an input stroke, as well as the use of color distance maps. The results presented in this paper shows that the method developed by Cerutti et al. (denoted Guided Active Contour), obtains the best score for almost all observation criteria. Finally, we detail our online benchmark composed of 14 unsupervised methods and 6 supervised ones.

Connected Filtering Based on Multivalued Component-Trees

In recent papers, a new notion of component-graph was introduced. It extends the classical notion of component-tree initially proposed in mathematical morphology to model the structure of gray-level images. Component-graphs can indeed model the structure of any-gray-level or multivalued-images. We now extend the anti extensive filtering scheme based on component-trees, to make it tractable in the framework of component-graphs. More precisely, we provide solutions for building a component-graph, reducing it based on selection criteria, and reconstructing a filtered image from a reduced component-graph. In this paper, we first consider the cases where component-graphs still have a tree structure; they are then called multivalued component-trees. The relevance and usefulness of such multivalued component-trees are illustrated by applicative examples on hierarchically classified remote sensing images.

A context-based approach for the classification of Satellite Image Time Series

Satellite Image Time Series (SITS) analysis is an important domain with various applications in land study. In the coming years, both high temporal and high spatial resolution SITS will be available. This article aims at providing both temporal and spatial analysis of SITS. We propose first segmenting each image of the series, and then using these segmentations in order to characterize each pixel of the data with a spatial dimension (i.e. with contextual information). Providing spatially characterized pixels, pixel-based temporal analysis can be performed. Experiments carried out with this methodology show the relevance of this approach and the significance of the resulting extracted patterns in the context of the analysis of SITS.

A histogram semantic-based distance for multiresolution image classification

Image classification methods based on histogram analysis generally require to use relevant distances for histogram comparison. In this article, we propose a new distance devoted to compare histograms associated to semantic concepts linked by (dis)similarity correlations. This distance, whose computation relies on a hierarchical strategy, captures the multilevel semantic relations between these concepts. It also inherits from the low complexity properties of standard bin-to-bin distances, thus leading to fast and accurate results in the context of multiresolution image classification. Experiments performed on satellite images emphasize the relevance and usefulness of the proposed distance.

Multi-image Segmentation: A Collaborative Approach Based on Binary Partition Trees

Image segmentation is generally performed in a “one image, one algorithm” paradigm. However, it is sometimes required to consider several images of a same scene, or to carry out several (or several occurrences of a same) algorithm(s) to fully capture relevant information. To solve the induced segmentation fusion issues, various strategies have been already investigated for allowing a consensus between several segmentation outputs. This article proposes a contribution to segmentation fusion, with a specific focus on the “n images” part of the paradigm. Its main originality is to act on the segmentation research space, i.e., to work at an earlier stage than standard segmentation fusion approaches. To this end, an algorithmic framework is developed to build a binary partition tree in a collaborative fashion, from several images, thus allowing to obtain a unified hierarchical segmentation space. This framework is, in particular, designed to embed consensus policies inherited from the machine learning domain. Application examples proposed in remote sensing emphasise the potential usefulness of our approach for satellite image processing.

Color Object Recognition Based on Spatial Relations between Image Layers

The recognition of complex objects from color images is a challenging task, which is considered as a key-step in image analysis. Classical methods usually rely on structural or statistical descriptions of the object content, summarizing different image features such as outer contour, inner structure, or texture and color effects. Recently, a descriptor relying on the spatial relations between regions structuring the objects has been proposed for gray-level images. It integrates in a single homogeneous representation both shape information and relative spatial information about image layers. In this paper, we introduce an extension of this descriptor for color images. Our first contribution is to consider a segmentation algorithm coupled to a clustering strategy to extract the potentially disconnected color layers from the images. Our second contribution relies on the proposition of new strategies for the comparison of these descriptors, based on structural layers alignments and shape matching. This extension enables to recognize structured objects extracted from color images. Results obtained on two datasets of color images suggest that our method is efficient to recognize complex objects where the spatial organization is a discriminative feature.

Directional Enlacement Histograms for the Description of Complex Spatial Configurations between Objects

The analysis of spatial relations between objects in digital images plays a crucial role in various application domains related to pattern recognition and computer vision. Classical models for the evaluation of such relations are usually sufficient for the handling of simple objects, but can lead to ambiguous results in more complex situations. In this article, we investigate the modeling of spatial configurations where the objects can be imbricated in each other. We formalize this notion with the term enlacement, from which we also derive the term interlacement, denoting a mutual enlacement of two objects. Our main contribution is the proposition of new relative position descriptors designed to capture the enlacement and interlacement between two-dimensional objects. These descriptors take the form of circular histograms allowing to characterize spatial configurations with directional granularity, and they highlight useful invariance properties for typical image understanding applications. We also show how these descriptors can be used to evaluate different complex spatial relations, such as the surrounding of objects. Experimental results obtained in the different application domains of medical imaging, document image analysis and remote sensing, confirm the genericity of this approach.

Bags of spatial relations and shapes features for structural object description

We introduce a novel bags-of-features framework based on relative position descriptors, modeling both spatial relations and shape information between the pairwise structural subparts of objects. First, we propose a hierarchical approach for the decomposition of complex objects into structural subparts, as well as their description using the concept of Force Histogram Decomposition (FHD). Then, an original learning methodology is presented, in order to produce discriminative hierarchical spatial features for object classification tasks. The cornerstone is to build an homogeneous vocabulary of shapes and spatial configurations occurring across the objects at different scales of decomposition. An advantage of this learning procedure is its compatibility with traditional bags-of-features frameworks, allowing for hybrid representations of both structural and local features. Classification results obtained on two datasets of images highlight the interest of this approach based on hierarchical spatial relations descriptors to recognize structured objects.

Multivalued Component-Tree Filtering

We introduce the new notion of multivalued component-tree, that extends the classical component-tree initially devoted to grey-level images, in the mathematical morphology framework. We prove that multivalued component-trees can model images whose values are hierarchically organized. We also show that they can be efficiently built from standard component-tree construction algorithms, and involved in antiextensive filtering procedures. The relevance and usefulness of multivalued component-trees is illustrated by an applicative example on hierarchically classified remote sensing images.