Real-time tracking of lace stretch using machine vision

The paper describe a computer vision based system for automatic lace scalloping. The main problem other than scalloping path detection in real-time is that of coping with material flexibility. This problem varies depending on the material type and the complexity of the lace pattern. The vision system has to work with many different patterns and sizes of lace as well as tolerating misalignment. In order to satisfy industrial requirements two main conditions must be satisfied. To achieve a sufficient degree of automation, first, the river must be found without prior knowledge of the lace pattern being scalloped. A fuzzy reasoning rule-based technique is applied to overcome the problems of material distortion. Next, finding the river location across the lace strip must be carried out in real-time. To achieve this, a novel approach called the line mapping method (LMM) is devised to speed up the search for the river in subsequent frames. Several experiments have been carried out using lace patterns of varying complexity. All cutting paths across the patterns were correctly found. Experimental results indicate that the river path can be successfully detected in different lace patterns in real time, while coping with lace distortion