• Mr.S Sreenivasulu
• A suresh
• K Venumadhav
• D Bhavyakanth Reddy.

Segmentation aim at partitioning area in the image it will be based on the shape ,color or texture.It is useful in many computer vision applications such as medical image analyzing, object detection and recognizing, forensic applications.content based image retrieval is used on the online clothing purchasing.Here our goal is to segment the clothing parts from the image on the background and the skin area.We need to detect the skin color and segment the skin from the image,and left the apparel parts in the image for matching processes.Here We Propose an improved threshold-based segmentation technique by adding a new constraint to the previous method to limit the skin tone selection.The technique improved the segmentation results correctly segmenting the apparels with the shade of purple, pale pink, and pinkish-yellow.By the simulation of the images showed that the proposed method increased the segmentation results by 27%.

SKIN SEGMENTATION, THRESHOLD-BASED SEGMENTATION, CBIR, GARMENT SEGMENTATION, GARMENT RETRIEVAL

"SKIN SEGMENTATION BASED ON IMPROVED THRESHOLDING METHOD", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 4, page no.171-174, April-2019, Available :http://www.jetir.org/papers/JETIRBC06027.pdf

"SKIN SEGMENTATION BASED ON IMPROVED THRESHOLDING METHOD", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 4, page no. pp171-174, April-2019, Available at : http://www.jetir.org/papers/JETIRBC06027.pdf