Construction and Optimization of Feature Descriptor Based on Dynamic Local Intensity Order Relations of Pixel Group

Abstract

With the prevalence of smart embedded systems, the amount of images being captured and processed on mobile devices have grown significantly in recent years. Image feature descriptors which play crucial roles in detection or recognition tasks are expected to exhibit robust matching performance while at the same time maintain reasonable storage requirement. Among the local feature descriptors that have been proposed previously, local intensity order patterns (LIOP) demonstrated superior performance in many benchmark studies. As LIOP encodes the ranking relation in a point set (with N elements), however, its feature dimension increases drastically (N!) with the number of a neighboring sampling points around a pixel. To alleviate the dimensionality issue, this paper presents a local feature descriptor by considering pairwise intensity relation in a pixel group, thereby reducing feature dimension to the order of $C^{N}_{2}$. In the proposed method, the threshold for assigning order relation is set dynamically according to local intensity distribution. Different weighting schemes, including linear transformation and Euclidean distance, have also been investigated to adjust the contribution of each pairing relation. Ultimately, dynamic local intensity order relations (DLIOR) pattern is devised to effectively encode intensity order relation of each pixel group. Experimental results indicate that DLIOR consumes less storage space than LIOP but achieves comparable or superior feature matching performance using benchmark data set.