Kmeans Clustering Segmentation on Water Microbial Image with Color and Texture Feature Extraction

Image segmentation is one of the analytical processes for digital image recognition, where this process divides into several unique regions based on homogeneous pixels. The grouping images colour, texture and shape features. Colour in processing very important because colour has many information humans can easily understand. various features, combining intensity grey (grayscale) binary (black white) values. However, feature extraction weaknesses. If object used a small si[1]ze range area, use features needs to be combined with extraction, maximized. This study uses process. It bacterial objects (microbes) from water, limited quality that tend difficult identify. space Gabor filter so produces high-quality accuracy. Good. L*a*b vector increase accuracy results showed resulted an 17.5% by testing cluster value 1.2.