Abstract

The objective of this research is to address the issue of automated selection of the optimal stretching position for leather during the leather toggling process. By analysing a substantial number of leather profiles and the actions involved in manual stretching and leather stretching, it has been determined that selecting appropriate stretching positions and intervals is the pivotal factor in enhancing leather yield. Through orthogonal experimentation, it has been deduced that the ideal distances between the stretching points on both sides of the head and tail, as well as on both sides of the body parallel to the midrib line, are 12cm and 9cm respectively. Building upon this, the study proposes an algorithm for identifying and locating the most suitable stretching positions based on the simplified skeleton method and the intersection method of drawn circles. The algorithm employs machine vision to obtain the initial image of the leather source, followed by preprocessing to eliminate image defects and accentuated contours. Subsequently, the thinning algorithm extracts the image skeleton, and the convolution operation filters out the ridges and limbs of the leather, resulting in the simplest skeleton that determines the requisite stretching points. Building upon the determination of the necessary stretching points, the remaining contour regions of the leather are established using the circle intersection method, thus obtaining the remaining stretching points. The identified algorithm for identifying the optimal stretching points in this study holds significant importance in the research and development of automated equipment for the leather stretching plate drying process, and serves as a valuable reference for enhancing leather yield and optimising the process.