Hopfield neural network based algorithms for image restoration andreconstruction. II. Performance analysis

Authors:
Yi Sun
Affiliations:
Dept. of Electr. Eng., City Coll. of New York, NY
Venue:
IEEE Transactions on Signal Processing
Year:
2000

Citing 0
Cited 5

Multiresolution Support for Adaptive Image Restoration Using Neural Networks

ICANN '02 Proceedings of the International Conference on Artificial Neural Networks
Image Restoration Using Neural Networks

IWANN '01 Proceedings of the 6th International Work-Conference on Artificial and Natural Neural Networks: Bio-inspired Applications of Connectionism-Part II
Two image restoration algorithms using variational PDE based neural network

IWCMC '07 Proceedings of the 2007 international conference on Wireless communications and mobile computing
A family of likelihood ascent search multiuser detectors: an upper bound of bit error rate and a lower bound of asymptotic multiuser efficiency

IEEE Transactions on Communications
An MLP neural net with L1 and L2 regularizers for real conditions of deblurring

EURASIP Journal on Advances in Signal Processing

Quantified Score

Hi-index	35.68

Visualization

Abstract

For pt. I see ibid., vol.48, no.7, p.2105-18 (2000). In this paper, we analyze four typical sequential Hopfield (1982) neural network (HNN) based algorithms for image restoration and reconstruction, which are the modified HNN (PK) algorithm, the HNN (ZCVJ) algorithm with energy checking, the eliminating-highest-error (EHE) algorithm, and the simulated annealing (SA) algorithm. A new measure, the correct transition probability (CTP), is proposed for the performance of iterative algorithms and is used in this analysis. The CTP measures the correct transition probability for a neuron transition at a particular time and reveals the insight of the performance at each iteration. The general properties of the CTP are discussed. Derived are the CTP formulas of these four algorithms. The analysis shows that the EHE algorithm has the highest CTP in all conditions of the severity of blurring, the signal-to-noise ratio (SNR) of a blurred noisy image, and the regularization term. This confirms the result in many previous simulations that the EHE algorithms can converge to more accurate images with much fewer iterations, have much higher correct transition rates than other HNN algorithms, and suppress streaks in restored images. The analysis also shows that the CTPs of all these algorithms decrease with the severity of blurring, the severity of noise, and the degree of regularization, which also confirms the results in previous simulations. This in return suggests that the correct transition probability be a rational performance measure