In this paper we present a new method to group self-similar SIFT features in images. The aim is to automatically build groups of all SIFT features with the same semantics in an image. To achieve this a new distance between SIFT feature vectors taking into account their orientation and scale is introduced. The methods are presented in the context of recognition of buildings. A first evaluation s...

The increasing amount of high resolution Earth Observation (EO) data during recent years, has brought the content analysis of the provided data into the spotlight. Most of the current content analysis is based on unsupervised methods (e.g., clustering). However, the structure discovered by these methods is not necessarily human understandable. Moreover, they require some prior knowledge of the ...

The Image Understanding Environment (IUE) project is a ve year program, sponsored by ARPA, to develop a common object-oriented software environment for the development of algorithms and application systems. This paper reviews the design of this system and provides an overview of the distributed implementation eeort currently underway at Amerinex AI, The ultimate goal of the project is to provid...

Colorado State University is initiating a new project on learning control strategies for object recognition. It is our belief that the current library of IU algorithms is su cient for solving many practical tasks if we can only learn to sequence them properly. We are investigating the use of open-loop and closed-loop control policies for sequencing IU algorithms, emphasizing the use of Markov d...

We posit that visually descriptive language offers computer vision researchers both information about the world, and information about how people describe the world. The potential benefit from this source is made more significant due to the enormous amount of language data easily available today. We present a system to automatically generate natural language descriptions from images that exploi...

Motion is an important signal for agents in dynamic environments, but learning to represent motion from unlabeled video is a difficult and underconstrained problem. We propose a model of motion based on elementary group properties of transformations and use it to train a representation of image motion. While most methods of estimating motion are based on pixel-level constraints, we use these gr...

Image Understanding is fundamental to systems that need to extract contents and infer concepts from images. In this paper, we develop an architecture for understanding images, through which a system can recognize the content and the underlying concepts of an image and, reason and answer questions about both using a visual module, a reasoning module, and a commonsense knowledge base. In this arc...

An object learning system for image understanding is proposed in this paper. The knowledge acquisition system is designed as a supervised learning task. Therefore, the role of the user as teacher of the system is emphasized, which allows to obtain the object description as well as to select the best recognition strategy for each specific object. An object description is acquired by considering ...

Many algorithms for both identifying and reconstructing a 3-D object are based on the 2-D silhouettes of the object. In general, identifying a nonconvex object using a silhouettebased approach implies neglecting some features of its surface as identification clues. The same features cannot be reconstructed by volume intersection techniques using multiple silhouettes of the object. This paper ad...

Existing prior domain knowledge represents a valuable source of information for image interpretation problems such as classifying handwritten characters. Such domain knowledge must be translated into a form understandable by the learner. Translation can be realized with Explanation-Based Learning (EBL) which provides a kind of dynamic inductive bias, combining domain knowledge and training exam...