Share Email Print
cover

Proceedings Paper

Automatic inspection of textured surfaces by support vector machines
Author(s): Sina Jahanbin; Alan C. Bovik; Eduardo Pérez; Dinesh Nair
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Automatic inspection of manufactured products with natural looking textures is a challenging task. Products such as tiles, textile, leather, and lumber project image textures that cannot be modeled as periodic or otherwise regular; therefore, a stochastic modeling of local intensity distribution is required. An inspection system to replace human inspectors should be flexible in detecting flaws such as scratches, cracks, and stains occurring in various shapes and sizes that have never been seen before. A computer vision algorithm is proposed in this paper that extracts local statistical features from grey-level texture images decomposed with wavelet frames into subbands of various orientations and scales. The local features extracted are second order statistics derived from grey-level co-occurrence matrices. Subsequently, a support vector machine (SVM) classifier is trained to learn a general description of normal texture from defect-free samples. This algorithm is implemented in LabVIEW and is capable of processing natural texture images in real-time.

Paper Details

Date Published: 10 September 2009
PDF: 11 pages
Proc. SPIE 7432, Optical Inspection and Metrology for Non-Optics Industries, 74320A (10 September 2009); doi: 10.1117/12.825194
Show Author Affiliations
Sina Jahanbin, The Univ. of Texas at Austin (United States)
Alan C. Bovik, The Univ. of Texas at Austin (United States)
Eduardo Pérez, National Instruments Corp. (United States)
Dinesh Nair, National Instruments Corp. (United States)


Published in SPIE Proceedings Vol. 7432:
Optical Inspection and Metrology for Non-Optics Industries
Peisen S. Huang; Toru Yoshizawa; Kevin G. Harding, Editor(s)

© SPIE. Terms of Use
Back to Top