-
[show abstract]
[hide abstract]
ABSTRACT: Cataloguing pattern and tiling designs using their geometrical features is an old research topic, whose main goal is the synthesis of new designs. However, little effort have been made to approach the inverse problem, this is the analysis of a design using image processing techniques. A set of structural descriptors for automatically classifying designs of textile and tile fabric is proposed. Graphic descriptors as parallelogram fundamental, design cluster, design symmetry axes etc., are properly re-defined in a new framework that, using the theory of symmetry groups, tries to describe the structure of a pattern design. We describe the sequence of operations introduced for the analysis and extraction of these structural descriptors and the methodology used in each stage, devoting special attention to the techniques used in the image segmentation, object extraction, and clustering stages. Experimental results with textile patrimony images and tile museum images are also included.
Pattern Recognition, 2004. ICPR 2004. Proceedings of the 17th International Conference on; 09/2004
-
[show abstract]
[hide abstract]
ABSTRACT: We present a methodology for tile image reconstruction. This methodology is integrated in a computer tool providing automatic image analysis. Both, the reconstruction and analysis methodologies are based on the application of the scientific theory of symmetry groups and are part of an integrated management system for pattern design in the tile industries. As image analysis advances, information is obtained concerning design structure that will allow us to restitute (recover missing motifs), unify (choose between different motifs that should be equal) and standardize (adjust motifs exactly to their symmetry axes and rotation centers). This methodology for tile image reconstruction has been tried with different Islamic mosaics from the Alhambra (Granada, Spain). Results based on these are given
Computer Graphics International, 2004. Proceedings; 07/2004
-
[show abstract]
[hide abstract]
ABSTRACT: Self-organizing feature maps (SOFM) are an important tool to
visualize high-dimensional data as a two-dimensional image. One of the
possible applications of this network is in image recognition. However,
this architecture presents some problems mainly due to border effects.
In this paper a new organization of the feature maps termed toroidal
self-organizing feature maps (TSOFM) is presented. Its main advantage
consists in the elimination of the border effects and, consequently, an
increase in the recognition rate. Another important aspect presented in
this paper is the measurement of how well networks are organized during
the training phase. This proposal has been experimented with using a
real data set
Neural Networks,1997., International Conference on; 07/1997
-
[show abstract]
[hide abstract]
ABSTRACT: ECGI is an error-correcting-based learning technique that aims at
obtaining structural finite-state models of (unidimensional) objects
from samples of these objects. The learning procedure captures certain
useful regularities of the training data in the object-models, while
also obtaining appropriate models of the `irregularities' (errors and
distortions) that these data tend to exhibit with respect to the learnt
object-models. In the test phase, both the object-models and the
corresponding error-models are cooperatively used to recognize new
objects through stochastic error-correcting parsing. The application of
ECGI to planar shape recognition is discussed and an example is given
which consists of the recognition of arabic numerals from 0 to 9 that
were handwritten by several writers. The results are compared with those
of another more conventional (non-structural) recognition technique
showing that not only ECGI clearly outperforms this technique, but it
also seems capable of providing greater recognition accuracy than many
other approaches reported in the literature
Grammatical Inference: Theory, Applications and Alternatives, IEE Colloquium on; 05/1993
-
[show abstract]
[hide abstract]
ABSTRACT: The application of the structural learning technique known as
error correcting grammatical inference to planar shape recognition is
discussed and illustrated with a non-trivial printed digit recognition
task. Experimental results are presented and compared with those of
other more conventional (non-structural) techniques, showing the new
technique to provide significantly improved performance
Pattern Recognition, 1992. Vol.II. Conference B: Pattern Recognition Methodology and Systems, Proceedings., 11th IAPR International Conference on;
-
[show abstract]
[hide abstract]
ABSTRACT: This paper deals with the development of computer vision techniques for tracking the position of rigid and non-rigid objects for real-time applications. The tracking approach is based on the application of discrete techniques relying on the correspondences between several feature points from frame to frame. A vectorial object model is introduced to exploit smooth motion constraints and support deformable motion. The tracking algorithm has been implemented using a PC computer equiped with specific image-processing hardware. To test the algorithm with real images a traffic-supervision application has been implemented. In this experiment the algorithm succesfully tracks images in which vehicle deformations are observed due to changes of perspective as result of motion.
