Defects in the fabrics during or after weaving reduce the quality of them. With the development of technology, the frequency of the defects seen in fabrics has decreased, but still occurs. In the process of detecting fabric defects, the quality control unit tries to detect fabric defects. This process is both personal and time consuming, leading to costly and personal Errors. For this reason, solutions have been proposed in studies to carry out and automate the process under computer control. In this study, fabric images are divided into blocks of equal sizes to find out whether there are any defects in the fabrics. The features, which are Extracted by applying feature extraction method to each block of the image, are inserted into the K-means clustering algorithm. Two different methods are applied for feature extraction (gray level co-formation matrix and median difference) and their performances have been compared. The success rate of detecting the defect increases up to 97.99% when the gray level co-occurrence matrix is used. The success rate of detecting the defect increases up to 86.91% when the median differences are used. In addition, In addition, when the success rates are calculated separately for the defects in the weft direction and the defects in the warp direction, it is concluded that the defects in the weft direction are easier to find than the defects in the warp direction.