Translator Disclaimer
3 May 2012 Fast texture evaluation of textiles using the GLBP technique in GPU architecture
Author Affiliations +
Commonly, visual inspection tasks in the textile industry are performed by human experts. The major drawback of this type of inspection is the human subjectivity, which affects accuracy and repeatability. Objectivity, accuracy and repeatability can be achieved by analysing visual characteristics of the products using computer vision. Particularly, automatic real time inspection systems based on texture analysis can be implemented using Local Binary Pattern (LBP) techniques. A recent variation of the LBP techniques, named Geometric Local Binary Pattern (GLBP) technique, showed an increase in the performance for detecting small changes of local texture. In this paper a real time implementation of the algorithm is presented by using a Graphic Processing Unit (GPU). The LBP and GLBP techniques are compared in terms of speed and accuracy while implemented on a Central Processing Unit (CPU) and GPU environments. Algorithms are tested for detecting defects in fabrics as well as for evaluating global deviations of texture, which are due to the degradation of the surface in carpets. Results show that higher discriminant power between similar textures is obtained when using the GLBP technique.
© (2012) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
S. A. Orjuela-Vargas, J. Triana-Martinez, J. A. Fernandez Gallego, J. Alvarez, B. Ortiz-Jaramillo, and W. Philips "Fast texture evaluation of textiles using the GLBP technique in GPU architecture", Proc. SPIE 8436, Optics, Photonics, and Digital Technologies for Multimedia Applications II, 84360F (3 May 2012);

Back to Top