HSOG: A Novel Local Image Descriptor Based on Histograms of the Second-Order Gradients - Archive ouverte HAL Access content directly
Journal Articles IEEE Transactions on Image Processing Year : 2014

HSOG: A Novel Local Image Descriptor Based on Histograms of the Second-Order Gradients

Di Huang
  • Function : Author
Chao Zhu
  • Function : Author
Yunhong Wang
  • Function : Author
Liming Chen

Abstract

Recent investigations on human vision discover that the retinal image is a landscape or a geometric surface, consisting of features such as ridges and summits. However, most of existing popular local image descriptors in the literature, e.g., SIFT, HOG, DAISY, LBP, and GLOH, only employ the first order gradient information related to the slope and the elasticity, i.e. length, area, etc. of a surface, and thereby partially characterize the geometric properties of a landscape. In this paper, we introduce a novel and powerful local image descriptor that extracts the Histograms of Second Order Gradients, namely HSOG, to capture the curvature related geometric properties of the neural landscape, i.e., cliffs, ridges, summits, valleys, basins, etc. We conduct comprehensive experiments on three different applications including the problem of local image matching, visual object categorization (VOC), and scene classification. The experimental results clearly evidence the discriminative power of HSOG as compared with its first order gradient based counterparts, e.g., SIFT, HOG, DAISY, and CS- LBP, and the complementarity in terms of image representation, demonstrating the effectiveness of the proposed local descriptor.
No file

Dates and versions

hal-01301110 , version 1 (11-04-2016)

Identifiers

Cite

Di Huang, Chao Zhu, Yunhong Wang, Liming Chen. HSOG: A Novel Local Image Descriptor Based on Histograms of the Second-Order Gradients. IEEE Transactions on Image Processing, 2014, 11, 23, pp.4680-4695. ⟨10.1109/TIP.2014.2353814⟩. ⟨hal-01301110⟩
77 View
0 Download

Altmetric

Share

Gmail Facebook X LinkedIn More