... USER: I'd better like to talk about another poster. GOLEM: Ok. Show me the poster yo... more ... USER: I'd better like to talk about another poster. GOLEM: Ok. Show me the poster you are interested in so I can see it. ... In Advances in Artificial Intelligence, Iberamia-2004, pages 974 983, 2004. [10] K. Rahmadi, HM Altab, N. Akio, and K. Yoshinori. ...
ABSTRACT Symmetry detection in 2D and 3D shapes has been a classical problem in computer vision, ... more ABSTRACT Symmetry detection in 2D and 3D shapes has been a classical problem in computer vision, computational geometry, and pattern recognition. One of the reasons of this interest, is because symmetry is related to the balance and harmony, and in most cases it is considered like a beautiful proportion. In this paper we present different methods to detect mirror and rotational symmetries in 2D and 3D open and closed curves, and in trees represented by means of the orthogonal direction change chain code. These methods detect both global and local symmetries. They can also detect the number and position of the axes of symmetry. They are simple, easy to implement and fast to execute.
ABSTRACT This paper describes a computational model named Dev E-R (Developmental Engagement-Refle... more ABSTRACT This paper describes a computational model named Dev E-R (Developmental Engagement-Reflection) that, inspired by Piaget’s theory, simulates the assimi-lation-accommodation adaptation process. It is implemented with a new extended version of the computational model of creativity known as Engagement-Reflection. That is, this model simulates adaptation as a creative activity. We introduce here the implementation of our model on an agent that is initialized with basic reflex conducts and that through the interaction with a 3D virtual world, it is able to build new behaviors autonomously. The new acquired skills, according to Piaget’s theory, are typically observed in children that have reached the second substage of the sensorimotor period.
... The system is designed in such a way that even a web-cam may be employed. Page 2. ... France ... more ... The system is designed in such a way that even a web-cam may be employed. Page 2. ... France (1995) 8. Wolf, J., Burgard, W., Burkhardt, H.: Robust vision-based localization for mobile robots using an image retrieval system based on invariant features. ...
In this paper, we address the problem of image categorization with a fast novel method based on t... more In this paper, we address the problem of image categorization with a fast novel method based on the unsupervised clustering of graphs in the context of both region-based segmentation and the constellation approach to object recognition. Such method is an EM central clustering algorithm which builds prototypical graphs on the basis of either Softassign or fast matching with graph transformations.
In this paper, we propose a simple and highly robust point-matching method named Graph Transforma... more In this paper, we propose a simple and highly robust point-matching method named Graph Transformation Matching (GTM) relying on finding a consensus nearest-neighbour graph emerging from candidate matches. The method iteratively eliminates dubious matches in ...
We present a quantitative approach to the measurement of shape dissimilarity between two 3D (thre... more We present a quantitative approach to the measurement of shape dissimilarity between two 3D (three-dimensional) curves. Any 3D con-tinuous curve can be digitalized and represented as a 3D discrete curve. Thus, a 3D discrete curve is composed of constant orthogonal ...
... USER: I'd better like to talk about another poster. GOLEM: Ok. Show me the poster yo... more ... USER: I'd better like to talk about another poster. GOLEM: Ok. Show me the poster you are interested in so I can see it. ... In Advances in Artificial Intelligence, Iberamia-2004, pages 974 983, 2004. [10] K. Rahmadi, HM Altab, N. Akio, and K. Yoshinori. ...
ABSTRACT Symmetry detection in 2D and 3D shapes has been a classical problem in computer vision, ... more ABSTRACT Symmetry detection in 2D and 3D shapes has been a classical problem in computer vision, computational geometry, and pattern recognition. One of the reasons of this interest, is because symmetry is related to the balance and harmony, and in most cases it is considered like a beautiful proportion. In this paper we present different methods to detect mirror and rotational symmetries in 2D and 3D open and closed curves, and in trees represented by means of the orthogonal direction change chain code. These methods detect both global and local symmetries. They can also detect the number and position of the axes of symmetry. They are simple, easy to implement and fast to execute.
ABSTRACT This paper describes a computational model named Dev E-R (Developmental Engagement-Refle... more ABSTRACT This paper describes a computational model named Dev E-R (Developmental Engagement-Reflection) that, inspired by Piaget’s theory, simulates the assimi-lation-accommodation adaptation process. It is implemented with a new extended version of the computational model of creativity known as Engagement-Reflection. That is, this model simulates adaptation as a creative activity. We introduce here the implementation of our model on an agent that is initialized with basic reflex conducts and that through the interaction with a 3D virtual world, it is able to build new behaviors autonomously. The new acquired skills, according to Piaget’s theory, are typically observed in children that have reached the second substage of the sensorimotor period.
... The system is designed in such a way that even a web-cam may be employed. Page 2. ... France ... more ... The system is designed in such a way that even a web-cam may be employed. Page 2. ... France (1995) 8. Wolf, J., Burgard, W., Burkhardt, H.: Robust vision-based localization for mobile robots using an image retrieval system based on invariant features. ...
In this paper, we address the problem of image categorization with a fast novel method based on t... more In this paper, we address the problem of image categorization with a fast novel method based on the unsupervised clustering of graphs in the context of both region-based segmentation and the constellation approach to object recognition. Such method is an EM central clustering algorithm which builds prototypical graphs on the basis of either Softassign or fast matching with graph transformations.
In this paper, we propose a simple and highly robust point-matching method named Graph Transforma... more In this paper, we propose a simple and highly robust point-matching method named Graph Transformation Matching (GTM) relying on finding a consensus nearest-neighbour graph emerging from candidate matches. The method iteratively eliminates dubious matches in ...
We present a quantitative approach to the measurement of shape dissimilarity between two 3D (thre... more We present a quantitative approach to the measurement of shape dissimilarity between two 3D (three-dimensional) curves. Any 3D con-tinuous curve can be digitalized and represented as a 3D discrete curve. Thus, a 3D discrete curve is composed of constant orthogonal ...
Uploads
Papers by Wendy Aguilar