Abstract | ||
---|---|---|
This paper presents a new set of three-dimensional rotation invariant texture descriptors based on the well-known local binary patterns (LBPs). In the approach proposed here, we extend an existing three-dimensional LBP based on the region growing algorithm using existing features developed exquisitely for two-dimensional LBPs (pixel intensities and differences). We have conducted experiments on a synthetic dataset of three-dimensional randomly rotated texture images in order to evaluate the discriminatory power and the rotation invariant properties of our descriptors as well as those of other two-dimensional and three-dimensional texture descriptors. Our results demonstrate the effectiveness of the extended LBPs and improvements against other state-of-the-art hand-crafted three-dimensional texture descriptors on this dataset. Furthermore, we prove that the extended LBPs can be used in medical datasets to discriminate between MR images of oxygenated and non-oxygenated brain tissues of newborn babies. Display Omitted A new set of three-dimensional fully rotation invariant LBP descriptors is proposed.Proven utility of the third dimension in local binary patternsImprovements against other state-of-the-art 3D texture descriptorsApplication to a clinical dataset of susceptibility-weighted MR brain images |
Year | DOI | Venue |
---|---|---|
2017 | 10.1016/j.imavis.2017.03.004 | Image Vision Comput. |
Keywords | Field | DocType |
Local binary patterns (LBPs),Three-dimensions,Rotation invariance,Texture classification | Computer vision,Pattern recognition,Region growing algorithm,Local binary patterns,Artificial intelligence,Pixel,Invariant (mathematics),Mathematics,Binary number | Journal |
Volume | Issue | ISSN |
62 | C | 0262-8856 |
Citations | PageRank | References |
2 | 0.36 | 19 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Leonardo Citraro | 1 | 2 | 0.36 |
Sasan Mahmoodi | 2 | 94 | 17.37 |
Angela Darekar | 3 | 2 | 1.03 |
Brigitte Vollmer | 4 | 2 | 0.36 |