Leaves shape classification using curvature and fractal dimension
ICISP'10 Proceedings of the 4th international conference on Image and signal processing
Fourier fractal descriptors for colored texture analysis
ACIVS'11 Proceedings of the 13th international conference on Advanced concepts for intelligent vision systems
A comparative study on multiscale fractal dimension descriptors
Pattern Recognition Letters
Texture analysis by multi-resolution fractal descriptors
Expert Systems with Applications: An International Journal
Hi-index | 0.00 |
Abstract. This article reports on the application of the recently introduced concept of multiscale fractal dimension (MFD) as a resource for quantifying three-dimensional gene expression patterns in embryonic development. While traditional fractal dimensions provide interesting possibilities for quantifying pattern complexity, as defined by the intensity in which the pattern interacts with its surrounding space, those approaches fail to take into account the important fact that natural objects are not perfectly self-similar. By expressing the fractal behavior explicitly in terms of the spatial scale, the MFD provides a more comprehensive and objective characterization of the complexity of natural data such as gene expression profiles. After presenting the MFD concept as well as a technique for its numerical estimation, the potential of this measure for objectively quantifying gene expression is discussed, and a complete example is provided regarding the three-dimensional expression of the myogenic marker gene Myf5 along successive somites in a mouse embryo. In this specific case, the adopted technique proved itself a useful means for identifying spatial variations of gene expression intensity.