Texture discrimination by Gabor functions
Biological Cybernetics
Multichannel Texture Analysis Using Localized Spatial Filters
IEEE Transactions on Pattern Analysis and Machine Intelligence
Unsupervised texture segmentation using Gabor filters
Pattern Recognition
Texture Features for Browsing and Retrieval of Image Data
IEEE Transactions on Pattern Analysis and Machine Intelligence
Filtering for Texture Classification: A Comparative Study
IEEE Transactions on Pattern Analysis and Machine Intelligence
Texture Classification by Wavelet Packet Signatures
IEEE Transactions on Pattern Analysis and Machine Intelligence
Unsupervised texture segmentation of images using tuned matched Gabor filters
IEEE Transactions on Image Processing
| Hi-index | 0.00 |
Bone strength is dependent on both its mass and architecture. In this study, a tool was developed that incorporates metrics associated with both of these features. To accomplish this, textural features of trabecular bone were extracted from stained bone images using Gabor wavelets. Gabor wavelets are 2-D spatial filters that are both frequency and orientation tunable. A texture feature vector was constructed that consists of localized texture energies along different orientations at different scales. The texture feature characterizes the spatial (regional) distributions of the constituent bone lattice in terms of their size, shape and orientation. Results indicated that wavelet analysis provides the insight of the frequency composition that can be localized to the pizel level. Bone mass can be discriminated by the averaged texture energy across all orientations. Dominant bone lattice orientation can be determined by the orientation with the maximal value of the averaged texture energy across all scales. A measure of anisotropy can be quantified by the span between the maximum texture energy and the minimum texture energy. This methodology has the potential to provide a tool for quantifying both bone mass and bone structural anisotropy.