Now showing items 1-5 of 5

    • Artificial intelligence and the future 

      Clocksin, William (Wadsworth, 2011-01-03)
    • Joint optimisation for object class segmentation and dense stereo reconstruction 

      Ladicky, L.; Sengupta, S.; Russell, C.; Sturgess, P.; Bastanlar, Yalin; Clocksin, William; Torr, P.H.S. (BMVA Press, 2010)
      The problems of dense stereo reconstruction and object class segmentation can both be formulated as Conditional Random Field based labelling problems, in which every pixel in the image is assigned a label corresponding to ...
    • Joint optimisation for object class segmentation and dense stereo reconstruction 

      Ladicky, L.; Sturgess, P.; Russell, C.; Sengupta, S.; Bastanlar, Yalin; Clocksin, William; Torr, P.H.S. (2012)
      The problems of dense stereo reconstruction and object class segmentation can both be formulated as Random Field labeling problems, in which every pixel in the image is assigned a label corresponding to either its disparity, ...
    • Maximization of mutual information for offline Thai handwriting recognition 

      Nopsuwanchai, Roongroj; Biem, Alain; Clocksin, William (2006)
      This paper aims to improve the performance of an HMM-based offline Thai handwriting recognition system through discriminative training and the use of fine-tuned feature extraction methods. The discriminative training is ...
    • Multidimensional histogram equalization and modification 

      McCollum, Anthony; Clocksin, William (Institute of Electrical and Electronics Engineers (IEEE), 2007)
      We describe an approach toward multidimensional histogram equalization for the enhancement of color and multispectral images, based on the histogram explosion algorithm. A development from first principles is presented. ...