Régis Clouard

Borg: a knowledge-based system for automatic generation of image processing programs

This article deals with the design of a system that automates the generation of image processing applications. Users describe tasks to perform on images and the system constructs a specific plan, which, after being executed, should yield the desired results. Our approach to this problem belongs to a more general category of systems for the supervision of a library of operators. The generation of an application is considered as the dynamic building of chains of image processing through the selection, parameter tuning and scheduling of existing operators. To develop such a system, we suggest to use a knowledge-rich resolution model and to integrate seven design rules. The Borg system has been developed following these prescriptions. It hinges on hierarchical, opportunistic and incremental planning by means of knowledge sources of the blackboard model, which enable to take into account the planning, evaluation and knowledge acquisition issues.

AN ONTOLOGY-BASED MODEL FOR REPRESENTING IMAGE PROCESSING APPLICATION OBJECTIVES

This paper investigates the types of information that are necessary and sufficient to design and evaluate image processing software programs, and proposes a representation of these information elements using a computational language performable by vision systems and understandable by experts. The language is built upon a formulation model which distinguishes the specification of a goal and the definition of an input image class. Goals are stated in terms of tasks together with result samples. Image classes are defined by both linguistic and iconic descriptions. The model is implemented as an OWL domain ontology which provides the primitives for the formulation language.

Human-computer interaction for the generation of image processing applications

The development of customized image processing applications is time consuming and requires high level skills. This paper describes the design of an interactive application generation system oriented towards producing image processing software programs. The description is focused on two models which constitute the core of the human-computer interaction. First, the formulation model identifies and organizes information that is assumed necessary and sufficient for developing image processing applications. This model is represented as a domain ontology which provides primitives for the formulation language. Second, the interaction model defines ways to acquire such information from end-users. The result of the interaction is an application ontology from which a suitable software is generated. This model emphases the gradual emergence of a semantics of the problem through purely symbolic representations. Based on these two models, a prototype system has been implemented to conduct experiments.

First steps toward automatic location of landmarks on X-ray images

We address the problem of locating some anatomical bone structures on lateral cranial X-ray images. These structures are landmarks used in orthodontic therapy. The main problem in this pattern recognition application is that the landmarks are difficult to distinguish on images even for the human expert, because of lateral projection of the X-ray process. We propose a 3 steps approach: the first step provides a statistical estimation of the landmarks, using an adaptive coordinates space; the second step computes a region of interest around the estimated landmark; and in the third step, each landmark is precisely located using its anatomical definition. This paper describes the two first generic steps and gives examples of the last step for two anatomical points.

Neighborhood graphs and image processing

Many image processing and image segmentation problems, in two or three dimensions, can be addressed and solved by methods and tools developed within the graph theory. Two types of graphs are studied: neighborhood graphs (with the duals Voronoi diagram and Delaunay graph) and adjacency graphs. In this paper, we propose an image representation based on graphs: the graph object, together with methods for attributing and weighting the graph, and methods to merge nodes, is defined within an object-oriented library of image processing operators. In order to demonstrate the interest of the approach, several applications dealing with 2D images are briefly described and discussed: we show that this change of representation can greatly simplify the tuning of image processing plans and how to replace complex sequences of image operators by one single basic operation on graphs. As results are promising, our library of graph operators is being extended to 3D images.

A mutual reference shape based on information theory

In this paper, we consider the estimation of a reference shape from a set of different segmentation results using both active contours and information theory. The reference shape is defined as the minimum of a criterion that benefits from both the mutual information and the joint entropy of the input segmentations and is then called a mutual shape. This energy criterion is here justified using similarities between information theory quantities and area measures, and presented in a continuous variational framework. This framework brings out some interesting evaluation measures such as the specificity and sensitivity. In order to solve this shape optimization problem, shape derivatives are computed for each term of the criterion and interpreted as an evolution equation of an active contour. Some synthetical examples allow us to cast the light on the difference between our mutual shape and an average shape. Our framework has been considered for the estimation of a mutual shape for the evaluation of cardiac segmentation methods in MRI.

Resolution of image processing problems by dynamic planning within the framework of the blackboard model

Recent works dealing with the development of automatic image processing (IP) systems not dedicated to any specific application are all based on the search of a plan of treatments adapted to the nature of the problem and the images, among a base of predefined plans. In our approach on the contrary, we are interested in solving IP problems by building plans of treatment in a dynamic way and to use explicit knowledge for reasoning. Our system hinges upon hierarchical, incremental, and opportunistic planning within the blackboard architecture. The system reasoning makes use of explicit knowledge about expertise in IP in order to find out and set the value of parameters and form a sequence of classical IP operators.

How to formulate image processing application

This paper presents an ontology-based system for helping inexperienced users formulate image processing applications. We propose models and their formalization through ontologies that identify and organize the necessary and sufficient information to design such applications. We also explain the interaction means that lead the user to give a good formulation of his/her application.