Rapid Extraction of Clothing Sample Profile Based on the Improved Canny Algorithm

Abstract

In order to reduce the difficulty of clothing diversity on the edge extraction link, this study proposes an improved Canny algorithm that segments the pattern, styles, and contours of the clothing image after creating a sample library of a women’s image. Extract, improve the accuracy of the edge, and reduce the noise formed by texture and clothing. The results show that in the simulation experiment, the contour extraction of multiple categories of clothing is carried out, and compared with the differential operator algorithm and Canny algorithm, the experimental results show that the improved algorithm can more accurately segment the edge of clothing, extract the style contour, and express the characteristics of clothing.