Privacy Based Digital Image Retrieval by Using Visual and Textual Features

Project Discription

Abstract— As the number of internet users are increasing day by day. So amount of data also increases, so fast response is desired by different users. So most of the researchers are working in relevant information retrival. This work focus on image retrieval based on visual and textual features. Here searching is done on the basis of the textual content first then visual feature values obtain from the query image are compare with the dataset filtered image similar visual feature values is consider as relevant and the most similar images is ranked first then next as second, other are done in similar fashion. Results shows that combination of both type of feature give more effective results as compare to single one. Algorithm for Re-Ranking by color and CCM Feature: Colure feature: By storing the pixel value in an image is nothing accept an representation of the color intensity at that point in an image. Because of the various image format pixel values are different for the same image. This can be understand as in RGB three matrix of same image are prepare for Red, Green, Blue matrix range of any pixel value is between 0-1. While in the case of the gray format it is of single matrix range of any pixel value is between 0-255.

Project Sample Image