Besides testing the performance ability of the six local shape descriptors described in Section 4.2, we examine the potential of MKL to fuse multiple features with different representation properties.
Cell nuclei were separated based on shape descriptors.
Inan, T. & Halici, U. 3-d face recognition with local shape descriptors.
The Zernike moment descriptor (ZMD), Fourier descriptor (FD), and wavelet descriptor (WD) are the most popular shape descriptors due to their outstanding properties in IP and PR.
Salazar, A., Cerón, A. & Prieto, F. 3d curvature-based shape descriptors for face segmentation: an anatomical-based analysis.
Ceron, A., Salazar, A. & Prieto, F. Relevance analysis of 3d curvature-based shape descriptors on interest points of the face.
Shape descriptors are adapted to surface regions and kernels on descriptor bags are used to perform the database classification.
Two shape descriptors, i.e., circle variance (CV) and rectangularity (R) were analysed using the fluorescence micrographs of the cell nuclei (Equations 1, 2, 3, 4, 5).
Digital images were analyzed using the Image J software (version 1.42q, National Institute of Health, Bethesda, MD, USA) and measured for shape descriptors (area, perimeter and circularity).
These invariants can be used as shape descriptors for dictionary matching.
