RESUMEN
In the digital optical microscope, the depth of field cannot clearly display all fibers in the same image, due to the thickness of nonwovens. A new multi-focus image fusion algorithm based on non-subsampled shearlet transform (NSST) is proposed to improve the quality of fused image, which realizes the fusion of a series of images taken from the same perspective and makes all fibers clearly within a single image. The rule of large absolute value is used to fuse the high frequency sub-band and the rule of large regional variance is used to fuse the low frequency sub-band. Comparing the method with other methods, the superiority of the method can be seen from several indicators of image quality evaluation. Based on the fused image, the diameter and orientation are measured by Hough transform and image preprocessing, and automatic measurement is realized. The porosity is measured by identifying pores, which is fast and convenient. Experiments show that the measurement of nonwoven fabric structure can be quickly achieved based on image processing.
