TY - GEN
T1 - Decoupled marginal distribution of gradient magnitude and laplacian of gaussian for texture classification
AU - Xue, Wufeng
AU - Mou, Xuanqin
AU - Zhang, Lei
PY - 2015/1/1
Y1 - 2015/1/1
N2 - We propose a novel descriptor for classification of texture images based on two isotropic low level features: the gradient magnitude (GM) and the Laplacian of Gaussian (LOG). The local descriptor is devised as the concatenation of the marginal distributions and a decoupled marginal distributions of the two features in local patch. The isotropic low level features and the computation of the two distributions ensure the rotation invariance and its robustness. To make the descriptors contrast invariant, within each image and across difference images of the same class, L2-normalization and Weber normalization are implied to the two features. After examined on three benchmark datasets, the proposed descriptor is showed to be more effective than other filter bank based features. Besides, the proposed descriptor can achieve very good performance even with small patch.
AB - We propose a novel descriptor for classification of texture images based on two isotropic low level features: the gradient magnitude (GM) and the Laplacian of Gaussian (LOG). The local descriptor is devised as the concatenation of the marginal distributions and a decoupled marginal distributions of the two features in local patch. The isotropic low level features and the computation of the two distributions ensure the rotation invariance and its robustness. To make the descriptors contrast invariant, within each image and across difference images of the same class, L2-normalization and Weber normalization are implied to the two features. After examined on three benchmark datasets, the proposed descriptor is showed to be more effective than other filter bank based features. Besides, the proposed descriptor can achieve very good performance even with small patch.
KW - Decoupled marginal distributions
KW - Gradient magnitude
KW - Laplacian of gaussian
KW - Texture classification
UR - http://www.scopus.com/inward/record.url?scp=84951310705&partnerID=8YFLogxK
U2 - 10.1007/978-3-662-48558-3_42
DO - 10.1007/978-3-662-48558-3_42
M3 - Conference article published in proceeding or book
SN - 9783662485576
T3 - Communications in Computer and Information Science
SP - 418
EP - 428
BT - Computer Vision CCF Chinese Conference, CCCV 2015, Proceedings
PB - Springer Verlag
T2 - 1st Chinese Conference on Computer Vision, CCCV 2015
Y2 - 18 September 2015 through 20 September 2015
ER -