Loei Fabric Weaving Pattern Recognition Using Deep Neural Network

Abstract

The Thai traditional woven fabrics are handicraft products indicate the flourish of Thai national culture and creativity of the nation. Many provinces have a long history of their own patterns on hand-woven fabric weaving style. One of the well-known provinces is Loei. Several villages produce their own unique styles in the woven pattern: Tai Loei, Tai Dam, or Tai Lue. Local people are able to recognize and distinguish the difference between these fabric groups but it is not easy for people from other areas, especially tourists to discriminate them. Moreover, the most complicated one is to train a machine to tell the difference between these fabric patterns. The issues about machine to classify the identity of something used to be the difficult problem in the area of pattern recognition and image classification. But the advancement in the popular algorithms of Deep Neural Network on image recognition opens the new opportunity to accomplish these problems with the greatly improved result. In this paper, we proposed to apply the Deep Neural Network techniques to solve Thai Loei woven fabric pattern recognition problem. For helping the machine to recognize the local weaving style and for the tourist to understand the exclusive on each local tradition.