Thread Position in High Precision CNC Sewing
CNC sewing technology is applied for assembling layers of textiles. Typical examples are car seats or mattresses. The most important function of the sewing thread is not to fix and connect the different layers, but to appear visually pleasing . Therefore, the final thread pattern must correspond to a model up to acceptable deviations, which are task specific . However, the elasticity of the materials causes pattern deformations due to geometric shifts of older stitches, if newer stitches are set within striking distance. In order to achieve an optimal appearance, it is necessary to account for these shifts and anticipate the deformation of the thread pattern within the CNC sewing program. Up to now, this is addressed by human experts in an iterative way. Using the current state of the CNC program, a specimen is created. Subsequently, the human expert inspects the specimen and modifies the program accordingly. The program modification is performed more or less intuitively and requires a lot of experience. This procedure is repeated as long as necessary and may take up to two days. Next to the time commitment, this trial and error approach comes along with a high material cost, since a sufficient amount of test samples is needed to optimize the CNC program.
The goal of this work is to automate the process of inspection and subsequent adaptation of the CNC program, with the final workflow being as follows: Given a new pattern, an initial sewing is performed using the desired model. This will result in a distorted thread pattern, as it is visualized in Figure 1. The specimen created this way is placed in a camera based inspection system. Based on the single specimen and given knowledge about the desired pattern, the inspection Fig. 1: An exemplary visualization of the distortions. The black line shows the desired thread pattern. However, sewing in such a pattern might actually lead to the distorted pattern shown in red. system automatically detects the real thread pattern using image processing techniques. Subsequently, a registration and adaptation of the desired model is performed, such that it optimally fits the detected thread pattern. Based on the calculated deformation, the CNC program required to achieve the desired pattern is calculated.
This paper focuses on the image processing part, including the image acquisition and model-based registration/adaptation. On the most abstract level, it can be separated into a hardware part, consisting of the construction of the camera based inspection system, and a software part, consisting of the image processing and model adaptation. Section II describes the inspection system and the image acquisition process. Image processing techniques to automatically detect the thread are described in Section III. A pipeline for the thread pattern registration and adaptation is proposed in Section IV. The presented inspection system does not only lay the foundation for the automated computation of the CNC program, but can be used as a standalone system for quality assurance.
Given arbitrary complex thread patterns, the system automatically detects the real world thread pattern and compares it with the pattern intended by the manufacturer. A deformation vector can be calculated for every individual stitch with an accuracy of up to 50µm. The system may serve as a stand-alone for quality assurance. However, it also lays the foundation for the automated correction of stitch positions in textiles distorted by the elasticity of the material. Based on the computed deformation vector field, an automated correction of the CNC program to create the desired pattern is possible. An obvious limitation of the proposed system is the requirement for the thread to appear visually different than the background tissue. However, this is not the case for a variety of products, for which the thread color is wanted to be identical to the background color. A typical example is a black car seat sewed using a black thread. We are currently working on exchanging the RGB-camera for a multi-spectral image acquisition in order to distinguish originally metamer, i.e. identical appearing, objects.
A camera based inspection system was introduced to automate the quality inspection process within the area of CNC sewing. Created thread patterns are automatically detected and compared against the intended pattern model. A deformation vector is computed for every individual stitch position. For both the thread detection as well as the model-based registration and adaptation, dedicated image processing pipelines were proposed.