2 November 2011 Image segmentation using a hybrid technique by combining optical and digital methods
Author Affiliations +
We present an image segmentation method based on the use of an optical technique for detection of contours (as a preprocessing stage) and a posterior digital segmentation algorithms. The contouring technique is utilized to find an accurate contour and it is based on the polarization features of the twisted-nematic liquid-crystal displays (TNLCDs). TN-LCDs are manufactured to work between a crossed polarizer-analyzer pair. When the analyzer is at 45 deg (instead of 90 deg) with respect to the polarizer, one obtains an optically processed image with pronounced outlines (dark contours) at middle intensity. On other hand, the segmentation algorithms are based on active shape models or snakes. Experimental results show that the proposed technique yields accurate segmentation for low-contrast images. Also, we demonstrate that this hybrid-system has a better performance than purely digital algorithms.
© (2011) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Juan Pablo Aguayo Adame, Juan Pablo Aguayo Adame, Jorge L. Flores, Jorge L. Flores, José A. Ferrari, José A. Ferrari, Guillermo García-Torales, Guillermo García-Torales, "Image segmentation using a hybrid technique by combining optical and digital methods", Proc. SPIE 8011, 22nd Congress of the International Commission for Optics: Light for the Development of the World, 801188 (2 November 2011); doi: 10.1117/12.903425; https://doi.org/10.1117/12.903425

Back to Top