Classification of textile images

ABSTRACT In this study, 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 are used for the classification. To detect line and circle features, 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 classified with circle feature. For the classification of the textile images, it is used some classification methods as Manual. Thresholding, Nearest Neighbor, ^-Nearest Neighbor, Minimum Distance. After the evaluation of the system, we have found that the best methods to classify striped images are "Nearest Neighbor with Manual Thresholding" and "^-Nearest Neighbor with Manual Thresholding and £=5, k=7, kr=\ 1". The best methods to classify plaided images are "Nearest Neighbor" and "Nearest Neighbor with Manual Thresholding". The best method to classify speckled images is "Manual Thresholding with Line and Circle Threshold > 0". The results of the classification are quite successful.