|International Journal of Computer Applications
|Foundation of Computer Science (FCS), NY, USA
|Volume 117 - Number 2
|Year of Publication: 2015
|Authors: Anita Ahmad Kasim, Retantyo Wardoyo, Agus Harjoko
Anita Ahmad Kasim, Retantyo Wardoyo, Agus Harjoko . Fuzzy C Means for Image Batik Clustering based on Spatial Features. International Journal of Computer Applications. 117, 2 ( May 2015), 1-4. DOI=10.5120/20523-2853
Patterns of batik produce geometric shapes unique, the number and name of the batik patterns make it difficult to recognize each motif. Spatial information is an important aspect of image processing such as computer vision and recognition structure / pattern in the context of modeling and resolution of the uncertainty caused by the ambiguity in the low-level features. Batik motifs are very diverse produce values that are sometimes not obvious feature class. There is a feature that is included in the value of two different classes. This causes an error in the process of cluster motif. The problems described above can be formulated problem in this research is how to build a cluster of batik images using fuzzy C means cluster based on spatial features. From the results of experiments that have been done obtained Fuzzy C Means able to build a cluster of batik based on the spatial characteristics of contrast, energy, correlation and homogeneity. Cluster obtained seen that the use of FCM in the cluster image Batik produces batik image data distribution in cluster grouping characteristic obvious visible difference.