Color Image Segmentation to the RGB and HSI Model Based on Region Growing Algorithm

Image segmentation is to divide the image into disjoint homogenous regions or classes, where all the pixels in the same class must have some common characteristics. In this paper, a new algorithm proposed to segment regions in an image, which is based on determining seed regions in an image. The algorithm applied on images of different complexity. The segmentation applied on each band of the RGB images, and also tested on the HSI images, the results showed that, we can obtain good segmentation by processing the intensity band of the HSI model, which gave similar results as that obtained in the RGB model. The results also showed the relationship between the number of dilation processing to close the regions and the number of regions that can be segmented, good result obtained with the number of dilation equal 2, this obtained experimentally, also the results showed the best value to expand pixel neighbor is from 1 to 4, after that the image will be degraded.