Clustering the pixel columns and rows of hand-written digit images

external image Img.log.msirm3.100.128-1diffG0.0.txt.png external image Img.log.msirm3.100.128-1diffG1.0.txt.png
external image Img.log.msirm3.100.128-1diffG2.0.txt.png external image Img.log.msirm3.100.128-1diffG3.0.txt.png
external image Img.log.msirm3.100.128-1diffG4.0.txt.png external image Img.log.msirm3.100.128-1diffG5.0.txt.png
external image Img.log.msirm3.100.128-1diffG6.0.txt.png external image Img.log.msirm3.100.128-1diffG7.0.txt.png
external image Img.log.msirm3.100.128-1diffG8.0.txt.png external image Img.log.msirm3.100.128-1diffG9.0.txt.png
   
  • This is a visualization of MNIST data clustering proposed in our work [Masada+ ICONIP2013].
  • Black pixels are the pixels detected as irrelevant by our method.
  • We can use clustering results for classifying test images.