• Anita Katkade
• Sneha Nikam
• Shweta Fugat
• Priyanka Daware

n many computer vision applications image segmentation is fundamental task. While performing any enhancement technique, it must be performed on whole image. Before enhancement the objects must be identified by photo applications to cover the entire image. A new unsupervised color image segmentation algorithm is used which gives the information in LCH – luminous, color, hue value is obtained by detecting edges in color images. To obtain group of non-overlapping segmentation of the image with segment tagged, image is to be broken into equal segments and find perceptual objects. Thus to output a non-overlapping segmentation of the image with segment tagged as a perceptual object, multi resolution merging is used which gives feature and information of color along with a region grown map.

Color Gradient, Entropy, Foliage Detection, Image Segmentation,Skin Detection, Sky Detection.

"Automatic Image Segmentation Using Feature Merging", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.2, Issue 4, page no.911-916, April-2015, Available :http://www.jetir.org/papers/JETIR1504011.pdf

"Automatic Image Segmentation Using Feature Merging", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.2, Issue 4, page no. pp911-916, April-2015, Available at : http://www.jetir.org/papers/JETIR1504011.pdf