Pattern-making simulation on embroidery using probabilistic neural network and texture fitting method

Embroidery fabric is different from other planar fabrics such as printed fabrics and twill fabrics. Because embroidery fabrics have inherent solid texture patterns, furry edges, voids and thickness shadows, it is very difficult to filter and simulate texture patterns and this is the bottleneck for embroidery automation. Therefore, this paper proposes the texture fitting method. The texture fitting method is a kind of nonfiltered digital image processing method. For embroidery fabrics full of multiple single-connected, single-color and single-texture closed regions, the texture fitting method can complete color and region separation, and texture simulation fast. Then the results can be output to monitors or plotters to investigate the simulation effect and it can be compared to real fabrics, or this technology can be used as a generalized filter for embroidery fabrics. This paper first addresses a combination of mean, morphological and central weighted median filters to remove light variation on embroidery surface, periodic darkness on the greige, and noised texture structures, so as to separate colors by weighted fuzzy C-means method and reshape one-dimensional image pixels to finish region separation. The second part of this paper utilizes the texture fitting method to identify stitch colors and simulate texture patterns over the whole image. By exporting the result to visual devices, we can prove the integral correctness and efficiency of the texture simulation.