Textile Image Classification: Categorizing huge amount of textile images efficiently

Today, according to the increasing development of the information technologies the number of the images in textile industry is rising very fast. It seems that the textile images cannot be processed with manually. It is required that textile images are categorized as suitable classes to profit from these images. In this book, it is explained how huge textile images are classified into striped, plaided and speckled image classes. Striped images are also categorized into the classes of horizontal, vertical, 45 and 135 degree lines. Line and circle features have been used for the classification methods. To detect line and circle features of the images, it is applied to line detection operator and Hough transform method respectively. With the line feature, striped and plaided images are classified, but speckled images are found with circle feature. For the classification of the textile images, some classification methods are used as Manual Thresholding, Nearest Neighbor, k-Nearest Neighbor, Minimum Distance. The system has been evaulated in detail, and the experimental results show that the developed system categorized the textile images successfully.