Journal of Computer Research and Development ›› 2014, Vol. 51 ›› Issue (9): 1891-1900.doi: 10.7544/issn1000-1239.2014.20140266
Special Issue: 2014深度学习
Next Articles
Lü Guohao, Luo Siwei, Huang Yaping, Jiang Xinlan
Online:
Abstract: Regularization method is widely used in solving the inverse problem. An accurate regularization model plays the most important part in solving the inverse problem. The energy constraints should be different for the different types of images and different parts of the same image, but the traditional L1 and L2 models used in the field of image restoration are both based on a single prior assumption. In this paper, according to the defects of the single priori assumption in traditional regularization model, a novel regularization method based on convolution neural network is proposed and applied to image restoration, therefore, the image restoration can be regarded as a classification issue. In this method, the image is partitioned into several blocks, and the convolution neural network is used to extract and classify the features of sub-block images; then the different forms of the priori regularization constraints are adopted considering the different features of the sub-block images, therefore the regularization method is no longer limited to a single priori assumption. Experiments show that the image restoration results by the regularization method based on convolution neural network are superior to those by the traditional regularization model with a single priori assumption. Therefore the regularization method based on convolution neural network can better restore image, maintain the edge texture characteristic of the image nicely, and has lower computational cost.
Key words: L1 norm constraint, L2 norm constraint, regularization method, convolution neural network, image restoration
CLC Number:
TP18
Lü Guohao, Luo Siwei, Huang Yaping, Jiang Xinlan. A Novel Regularization Method Based on Convolution Neural Network[J]. Journal of Computer Research and Development, 2014, 51(9): 1891-1900.
0 / / Recommend
Add to citation manager EndNote|Reference Manager|ProCite|BibTeX|RefWorks
URL: https://crad.ict.ac.cn/EN/10.7544/issn1000-1239.2014.20140266
https://crad.ict.ac.cn/EN/Y2014/V51/I9/1891