Paper Details

The content based image retrieval (CBIR) is one of the most popular, rising researchareas of the digital imageprocessing. . The goal of CBIR is to extract visual contentof an image automatically, like color, texture, or shape.With thehelp of theexisting methods, describe a possible solution how to design and implement a taskspecific descriptor, which canhandle the informational gap between a sketch and acolored image, making an opportunity for the efficient search hereby.We investigatethe problem of fine-grained sketch-based image retrieval (SBIR), where free-handhuman sketches are used asqueries to perform instance-level retrieval of images.In this work, a novel index structure and the corresponding rawcontour-basedmatching algorithm are proposed to calculate the similarity between a sketch queryand natural images, andmake sketch-based image retrieval scalable to millions ofimages.We have studied EHD, HOG and SIFT. Overall, the resultsshow that thesketch based system allows users an intuitive access to The SBIR technology can beused in several applicationssuch as digital libraries, crime prevention, photo sharingsites. Such a system has great value in apprehending suspects andidentifying victimsin forensics query picture intensified recently, which demands on the quite widemethodology spectrum onthe area of the image processing.

Mrs.S.N.Zaware, Saurabh Bhilare, Janhavi Kolte, Rahul Chaudhari, Pranita Deokar, “Sketch Based Shopping (SBS)”, International Journal of Advance Engineering and Research Development (IJAERD), Vol. 4, Issue 12, pp. -, December 2017.