Information measure based tone mapping of outdoor LDR image for maximum scale‐invariant feature transform extraction

Abstract

A novel tone mapping method referred to here as information measure-based tone mapping is proposed for extracting the maximum number of scale-invariant feature transform (SIFT) feature points from outdoor low dynamic range (LDR) images. To this end, first, an image is transformed to YUV colour space in which every pixel is assigned two information scores: forward and inverse scores. The forward and inverse information scores represent the number of neighbour pixels that differ in their intensities from the pixel under consideration by a certain threshold for the respective YUV and inverse YUV images. The proposed tone mapping is then carried out in such a way as to emphasise the pixels of high information scores defined by a weighted sum of forward and inverse information scores. Experimental results show that the proposed method offers superior performance to state-of-the-art methods in terms of the number of features extracted and matched.