Lookup Table LUT Method for Inverse Halftoning

1
Look-up Table (LUT) Method for Inverse Halftoning

• M. Mese and P.P. Vaidyanathan
• IEEE Transactions on Image Processing, Volume
  10, Issue 10, Oct. 2001, Pages 1566-1578
• Electrical Engineering Department, California
  Institute of Technology
• Speaker Jen-Bang Feng

2
Outline

• Halftone Techniques
• Look Up Table
• Experimental Results
• Conclusions

3
Halftone and Inverse Halftone
Grayscale
Halftone
Binary
Inverse Halftone
Grayscale
4
Halftone Classification

• Blind
• Statistical, Wavelet, LUT
• Non-blind
• Statistical, Wavelet, Adaptive, Nonlinear
• By the information of halftone kernel

5
Look Up Table (LUT)

• Fast, parallel, less computation
• Training the LUT first
• Look up the table
• Choose the neighborhood or template (a collection
  of pixels) in the prediction.

6
LUT Process
For ex.
are in training Sample. Then O 50 if this block
appears
If (p0,p1,,pn-1) exists if not, use white/black
ratio
n 16
n 19
O denotes the estimated pixel.
7
Experimental Results
PSNR30.41 dB
PSNR24.42 dB
8
Conclusions

• Inversed images are naturally blurred.
• Edge is the key point.
• Almost all schemes try to
• locate the edge
• Enhance the edge or enhance the background