Abstract | BTC | Data Set Description | Our Approach |
Simulation Results | Conclusions | Computer Programs | Division of labor |
References |
|
|
|
This report describes our attempt to apply ANFIS (Adaptive Neuro-Fuzzy Inference Systems)
[Jang93] for the prediction of best threshold for the BTC (Block Truncation Coding) System. The preliminary results show that ANFIS is a competitive approach when compared to conventional approaches.
so =98.75 ; =92.95 ;q=7
and a=16.7≒17 ; b=204.2≒04
the bit plane is
The reconstructed block becomes:
And the sample mean and variance are preserved.
This project tries to solve the problem of the threshold prediction using the ANFIS
[Jang93] approach. We try to train the best threshold by ANFIS.3-input and each input with 2 Generalized bell member function
Lena as training |
Lena |
Fruit.raw |
Bridge |
Optimal |
30.5441 |
33.1529 |
28.3928 |
BTC |
29.7393 |
32.6486 |
27.7932 |
FBTC with 20 epoch |
30.0157 |
32.7851 |
27.9352 |
FBTC with 100 epoch |
30.0120 |
32.7773 |
27.9271 |
Lena+fruit.raw+bridge.256 as training data |
Lena |
Fruit.raw |
Bridge.256 |
Hat.256 |
Optimal |
30.5441 |
33.1529 |
28.3928 |
30.9963 |
BTC |
29.7393 |
32.6486 |
27.7932 |
30.4289 |
FBTC with 20 epochs |
29.9896 |
32.8191 |
27.9789 |
30.6274 |
FBTC with 50 epochs |
29.9826 |
32.8258 |
27.9803 |
30.6279 |
We think ANFIS is useful because it improve the PSNR about 0.25db
(Actually, an approach that can improve PSNR much is very hard to create.) It uses twice time to run FBTC than BTC but only uses one-third time to get optimal BTC.
We want to improve the performance by using another feature as inputs and run simulation with bigger image, maybe 512x512 or so…