Single-Frame Text Super-Resolution: A Bayesian Approach

    •  Gerald Dalley, Bill Freeman, Joe Marks, "Single-Frame Text Super-Resolution: A Bayesian Approach", Tech. Rep. TR2004-129, Mitsubishi Electric Research Laboratories, Cambridge, MA, October 2004.
      BibTeX TR2004-129 PDF
      • @techreport{MERL_TR2004-129,
      • author = {Gerald Dalley, Bill Freeman, Joe Marks},
      • title = {Single-Frame Text Super-Resolution: A Bayesian Approach},
      • institution = {MERL - Mitsubishi Electric Research Laboratories},
      • address = {Cambridge, MA 02139},
      • number = {TR2004-129},
      • month = oct,
      • year = 2004,
      • url = {}
      • }
  • Research Area:

    Computer Vision


We address the problem of text super-resolution: given a single image of text scanned in at low resolution from a piece of paper, return the image that is mostly likely to be generated from a noiseless high-resolution scan of the same piece of paper. In doing so, we wish to: (1) avoid introducing artifacts in the high-resolution image such as blurry edges and rounded corners, (2) recover from quantization noise and grid-alignment effects that introduce errors in the low-resolution image, and (3) handle documents with very large glyph sets such as Japanese's Kanji. Applications for this technology include improving the display of: fax documents, low-resolution scans of archival documents, and low-resolution bitmapped fonts on high-resolution output devices.