Abstract:

Texture identification and matching a sample fabric within a known collection of produced fabrics is a time-consuming and difficult process as a human activity. In this study, a computational method for textile texture identification is introduced using an image analysis technique. For this purpose, images of fabrics were captured by a digital flat scanner. Texture features were extracted using the Edge frequency and Gray Level Co-occurrence Matrix (GLCM) methods. In this way, a library of texture features was collected. To match a new texture with library samples, the closest texture feature based on Euclidian distance was identified as the fabric texture. Experimental results for 33 different textures showed the successful identification of textures with both methods. However, the edge frequency method is more feasible and acceptable due to its computational simplicity and lower processing time. In addition, it was shown that the edge frequency method is extremely insensitive to the colour and scanning direction of the fabric.