This paper presents a generic cognitive vision platform for the automatic recognition of natural complex objects. The recognition consists of three steps : image processing for numerical object description, mapping of numerical data into symbolic data and semantic interpretation for object recognition. The focus of this paper is the distributed platform architecture composed of three highly specialized Knowledge Based Systems (KBS). The first KBS is dedicated to semantic interpretation. The second one has to deal with the anchoring of symbolic data into image data. The last KBS is dedicated to intelligent image processing. After a brief overview of the natural object recognition problem, this paper describes the three subcomponents of the platform. Keywords : Cognitive Vision, Natural Object Recognition, Knowledge Based System 1.

High-level vision systems use object, scene or domain specific knowledge to interpret images. Unfortunately, this knowledge has to be acquired for every domain. This makes it difficult to port systems from one domain to another, and therefore to compare them. Recently, the authors of the ADORE system have claimed that object recognition can be modeled as a Markov decision process, and that domain-specific control strategies can be inferred automatically from training data. In this paper we demonstrate the generality of this approach by porting ADORE to a new domain, where it controls an object recognition system that previously relied on a semantic network.

This paper addresses the 3D object recognition problem modelled as a Constraint Satisfaction Problem. In this setting, each object view can be modelled as a constraint graph where nodes are object parts and constraints are topological and geometrical relationships among them. By modelling the problem as a CSP, we can recognize an object when all constraints are satisfied by exploiting results from the CSP field. However, in classical CSPs variable domains have to be statically defined at the beginning of the constraint propagation process. Thus, not only feature acquisition should be completed before the constraint solving process starts, but all image features should be extracted even if not belonging to significant image parts. In visual applications, this requirement turns out to be inefficient since visual features acquisition is a very time consuming task. We present an Interactive Constraint Satisfaction model for problems where variable domains may not be completely known at the beginning of the computation, and can be interactively acquired during the computational process only when needed (on demand). The constraint propagation process works on already known domain values and adds new constraints on unknown domain parts. These new constraints can be used to incrementally process new information without restarting the constraint propagation process from scratch each time new information is available. In addition, these constraints can guide the feature acquisition process, thus focussing attention on significant image parts. We present the Interactive CSP model and a propagation algorithm for it. We propose an implementation of the framework in Constraint Logic Programming on Finite Domains, CLP(FD).

Abstract. Automated image interpretation is an important task in numerous applications ranging from security systems to natural resource inventorization based on remote-sensing. Recently, a second generation of adaptive machine-learned image interpretation systems have shown expert-level performance in several challenging domains. While demonstrating an unprecedented improvement over hand-engineered and first generation machine-learned systems in terms of cross-domain portability, design-cycle time, and robustness, such systems are still severely limited. This paper inspects the anatomy of the state-of-the-art Multi resolution Adaptive Object Recognition framework (MR ADORE) and presents extensions that aim at removing the last vestiges of human intervention still present in the original design of ADORE. More specifically, feature selection is still a task performed by human domain experts and represents a major stumbling block in the creation process of fully autonomous image interpretation systems. This paper focuses on minimizing such need for human engineering. After discussing experimental results, showing the performance of the framework extensions in the domain of forestry, the paper concludes by outlining autonomous feature extraction methods that may completely remove the need for human expertise in the feature selection process.

The paper presents a hierarchical object recognition system for document processing. It is based on a spatial tree structure representation and Bayesian framework. The image components are built up from lower level image components stored in a library. The tree representations of the objects are assembled from these components. A probabilistic framework is used in order to get robust behaviour. The method is able to convert general circuit diagrams to their components and store them in a hierarchical datastructure. The paper presents simulation for extracting the components of sample circuit diagrams.

Abstract Automated image interpretation is an important task innumerous applications ranging from security systems to natural resource inventorization based on remote-sensing.Recently, a second generation of adaptive machine-learned image interpretation system (ADORE) has shown expert-level performance in several challenging domains. Its extension, MR ADORE, aims at removing the last vestiges ofhuman intervention still present in the original design of ADORE. Both systems treat the image interpretation pro-cess as a sequential decision making process guided by a machine-learned heuristic value function. This paper em-ploys a new leveraging algorithm for regression (R ESLEV)to improve the learnability of the heuristics in MR ADORE. Experiments show that RESLEV improves the system's per-formance if the base learners are weak. Further analysis discovers the difference between regression and decision-making problems, and suggests an interesting research direction. Keywords: adaptive image interpretation system, leverag-ing for regression, boosting, sequential decision making. 1.

This paper presents an original approach for the symbol grounding problem involved in semantic image interpretation, i.e. the problem of the mapping between image data and semantic data. Our approach involves the following aspects of cognitive vision: knowledge acquisition and knowledge representation, reasoning and machine learning. The symbol grounding problem is considered as a problem as such and we propose an independent cognitive system dedicated to symbol grounding. This symbol grounding system introduces an intermediate layer between the semantic interpretation problem (reasoning in the semantic level) and the image processing problem. An important aspect of the work concerns the use of two ontologies to make easier the communication between the different layers: a visual

Automated image interpretation and object recognition is an important task in numerous applications ranging from security systems to natural resource inventorization based on remotesensing. Recently, a second generation of adaptive machine-learned image interpretation systems have shown promising performance in several challenging domains. While demonstrating an unprecedented improvement over handengineered or first generation machine learned systems in terms of cross-domain portability, design cycle time, and robustness, such systems are still severely limited. In this paper we pose several open challenges critical to further progress in learning vision systems. The issues are illustrated with recent efforts and examples.

Automated image interpretation is an important task in numerous applications ranging from security systems to natural resource inventorization based on remote-sensing. Recently, a second generation of adaptive machine-learned image interpretation systems have shown expert-level performance in several challenging domains. While demonstrating an unprecedented improvement over hand-engineered and first generation machine-learned systems in terms of cross-domain portability, design-cycle time, and robustness, such systems are still severely limited. This paper reviews the anatomy of the state-of-theart Multi resolution Adaptive Object Recognition framework (MR ADORE) and presents extensions that aim at removing the last vestiges of human intervention still present in the original design of ADORE. More specifically, feature selection is still a task performed by human domain experts thereby prohibiting automatic creation of image interpretation systems. This paper focuses on autonomous feature extraction methods aimed at removing the need for human expertise in the feature selection process.

We present a modular architecture for image understanding and active computer vision which consists of three major components: Sensor and actor interfaces required for data-driven active vision are encapsulated to hide machine-dependent parts; image segmentation is implemented in object-oriented programming as a hierarchy of image operator classes, guaranteeing simple and uniform interfaces; knowledge about the environment is represented either as a semantic network or as statistical object models or as a combination of both; the semantic network formalism is used to represent actions which are needed in explorative vision. We apply