A new quantitaive method to evaluate seam pucker with five shape parameters is proposed using three-dimensional imge anlaysis and artificaial intelligence. The shape parameters include the number of wave generating points, the wave amplitudes, and the wavelengths on the line next to the seam and on the edge line. Measrued shapes of puckered fabrics are converted into numericla dta in the three-dimensional corrdinate system, and the data are transformed into power spectra using fast Fourier transformation. Also, artificial intelligence techniques, including neural networks and fuzzy logic (or neurofuzzy algorithm), are used to recognize the characteristics of seam pucker. To obtain better quantitiative evaluations of seam pucker, 300 neurofuzzy engiens ar econstructed and tranied using reference puckered shapes produced by the simulator described in Part I. Power spectra of the measured data are transformed into specified fuzzy pattern through the fuzzification process to train the neurofuzzy engiens. The five shape parameters of puckered shapes are obtained from pattern recognition by the tranied neurofuzzy engines through the defuzification procsss.
展开▼