High Definition Metrology Based Surface Quality Control and Applications by Shichang Du & Lifeng Xi

Author:Shichang Du & Lifeng Xi
Language: eng
Format: epub
ISBN: 9789811502798
Publisher: Springer Singapore

5.3.2 The Framework of the Proposed Classification System

This subsection presents an overview of the proposed classification system with components of NSCT and an SVM classifier based on APSO-VSPS algorithm. To be specific, in feature extraction, high-resolution images are reflected by 3D coordinates of workpiece surfaces, which are filtered to extract details in different directions and scales by NSCT. The means and standard deviations of the coefficients of the wavelet sub-bands are calculated as feature vectors to represent a given surface. In the proposed classification method, the APSO algorithm is the main algorithm to select the optimal combination of parameters and the VSPS algorithm is nested in the main algorithm to improve the efficiency and accuracy of the search by its good performance in local search. The framework of the proposed system is shown in Fig. 5.23.

Fig. 5.23The framework of the workpiece surface classification system.

Reprinted from Ref. [112], copyright 2015, with permission from IEEE

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.