A key strength of our MorphoGraphX software is the ability to accurately extract curved surface meshes from 3D volumetric data and perform image processing on the resulting curved (2.5D) surface images.
To our surprise, the extracted curve shape in Fig. 3 a is quite different from that in Fig. 3 b.
Subsequently, this study proposes a wrinkle modeling method based on automatically extracted curves and improved shape control functions.
The average curve-to-curve ratios are utilized to describe the relationship of the extracted curves and fault diagnosis can then be achieved by comparing the ratios to the fault characteristic coefficients.
The extracted curves in Fig. 2 d exhibit symmetric Gaussian-like distribution, and the directions corresponding to electric fields of + 4 and −4 V/cm are opposite, being consistent with the mechanism of AHE.
Open image in new window Figure 3 FTIR spectra of (curve a) Acacia nilotica leaf extract and (curve b) stabilized AuNPs.
Since the ε-sublevel of this evolution contains the curve, the next step is to extract the curve itself by following an optimal trajectory inside each ε-sublevel.
The above two feature extraction methods are used to extract the curve eigenvectors of the experimental data (down-hole dynamometer cards) to structure the data set (different fault types of down-hole dynamometer cards with different data distribution).
