Linear models of cumulative distribution function for content-based medical image retrieval

We propose an Image matching technique based on Cumulative Distribution Function, which provides a considerable reduction in the retrieval time. The two novel approaches called bit plane histogram and hierarchical bit plane histogram are discussed. Next, the image matching technique based on Cumulative Distribution Function is explained and a comparison of the various techniques is brought out. The CDF of the query and the images in the database are approximated by piecewise linear models with two parameters, slope and intercept at various grayscale intervals. The contiguous set of lines approximating the CDFs enables us to compare the query image and the images in the database with corresponding estimated slopes and intercepts. As the dynamic range of CDF is from 0 to 1, images of different sizes can be compared. Approximation of CDFs with lines further reduces the dimension of the image features and thus improves the speed of matching.