TY - JOUR

T1 - An Efficient Topological Characterization of Gray-Levels Textures, Using a Multiresolution Representation

AU - Pikaz, Arie

AU - Averbuch, Amir

PY - 1997/1

Y1 - 1997/1

N2 - For a given textured image we define a sequence of graphs {Ns(t)}s∈I (called MRCG), where Ns(t) is the number of 4-connected components with size ≥s, for the images thresholded with t. The sequence of graphs are computed in almost linear time complexity, where the input size is the number of pixels of the image, using only integer arithmetic. The MRCG is a multiresolution representation, which is very useful for texture characterization. Its properties as a texture characterizer are analyzed and demonstrated.

AB - For a given textured image we define a sequence of graphs {Ns(t)}s∈I (called MRCG), where Ns(t) is the number of 4-connected components with size ≥s, for the images thresholded with t. The sequence of graphs are computed in almost linear time complexity, where the input size is the number of pixels of the image, using only integer arithmetic. The MRCG is a multiresolution representation, which is very useful for texture characterization. Its properties as a texture characterizer are analyzed and demonstrated.

UR - http://www.scopus.com/inward/record.url?scp=0030861195&partnerID=8YFLogxK

U2 - 10.1006/gmip.1996.0410

DO - 10.1006/gmip.1996.0410

M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???

AN - SCOPUS:0030861195

SN - 1077-3169

VL - 59

SP - 1

EP - 17

JO - Graphical Models and Image Processing

JF - Graphical Models and Image Processing

IS - 1

ER -