A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is
In this paper, we introduce a novel and powerful local image descriptor that extracts the histograms of second-order gradients (HSOGs) to capture the curvature related geometric properties of the neural ... gradient location and orientation histogram, only employ the first-order gradient information related to the slope and the elasticity, i.e., length, area, and so on of a surface, and thereby partially ... HSOG: A Novel Local Image Descriptor Based on Histograms of the Second-Order Gradients in computer vision, ranging from traditional vision tasks, e.g., panoramic stitching  , wide-baseline matching ...doi:10.1109/tip.2014.2353814 pmid:25203990 fatcat:l4r5cmcgzfagxdoiabrik2swom
In this paper, two novel local image region descriptors called Local Intensity Order-based Center Symmetric Local Binary Patterns (LIOCSLBP) and Local Intensity Order-based Orthogonally Combined Local ... Extensive experiments are conducted to evaluate the performance of the proposed descriptors on standard benchmark datasets for image matching, object recognition and scene recognition against the state-of-the-art ... In contrast, HSOG  used the second-order gradients to compute the Histogram of Second Order Gradients. ...doi:10.14738/aivp.53.3279 fatcat:rypreie43jdkzpzdfgu7ftjmmq
The major goal of the paper is to present a unique survey of the state-of-the-art image matching methods based on feature descriptor, from which future research may benefit. ... The current and future challenges of local feature descriptors are discussed. ...  suggested a novel and powerful local image descriptor for making use of the histograms of the second order gradients (HSOGs) to capture curvature related local geometric properties. ...doi:10.1109/access.2018.2888856 fatcat:rshfx326izcfdgk5ed6umit7wi