Automatic Identification of Weave Patterns of Checked and Colored Fabrics Using Optical Coherence Tomography

Identifying the weave pattern of fabrics can be done manually or automatically. Carrying out the weave recognition automatically will reduce the procedure time and error rates since automatic systems can perform successive measurements at high speeds and with great repeatability and quality. Woven fabric repeat identification systems that are automatic, usually work by employing complex algorithms and techniques. It is known that these automatic techniques struggle when trying to identify highly complex patterns, composing of a combination of different structures, figures, and colors. For example, image processing algorithms are known to make errors when dealing with checked and colored fabrics. In this paper, we apply the spectral domain optical coherence tomography imaging technique for identifying checked and colored woven fabric repeat automatically. This is achieved by employing an in-house written JAVA code that extracts the weave pattern from the tomography images. We show that automatic identification of weave pattern of checked and colored fabrics can be performed nondestructively by employing optical coherence tomography.