Title :
Structural description of textile and tile pattern designs using image processing
Author :
Valiente, José M. ; Albert, Francisco ; Carretero, Carmen ; Gomis, Jose M.
Author_Institution :
DISCA, Univ. Politecnica de Valencia, Spain
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.
Keywords :
cataloguing; computational geometry; fabrics; feature extraction; image classification; image colour analysis; image segmentation; inverse problems; pattern clustering; tiles; design cluster; design symmetry axes; geometrical features; graphic descriptors; image colour analysis; image processing techniques; image segmentation; inverse problem; object extraction; parallelogram fundamental; pattern cataloguing; pattern clustering; structural descriptor analysis; structural descriptor extraction; textile fabric; textile patrimony images; textile pattern design; theory of symmetry groups; tile fabric; tile museum images; tile pattern designs; Fabrics; Graphics; Image analysis; Image processing; Image segmentation; Image sequence analysis; Inverse problems; Process design; Textiles; Tiles;
Conference_Titel :
Pattern Recognition, 2004. ICPR 2004. Proceedings of the 17th International Conference on
Print_ISBN :
0-7695-2128-2
DOI :
10.1109/ICPR.2004.1334175