Using feed forward multilayer neural network and vector quantization as an image data compression technique

被引：0

作者：

Saad, EM ^{[1
]}

Deyab, MA ^{[1
]}

Abdelwahab, AA ^{[1
]}

机构：

[1] Helwan Univ, Fac Engn, Dept Telecomm & Elect, Cairo, Egypt

来源：

THIRD IEEE SYMPOSIUM ON COMPUTERS AND COMMUNICATIONS, PROCEEDINGS | 1998年

关键词：

image compression; neural networks; vector quantization;

D O I：

10.1109/ISCC.1998.702592

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Single hidden layer feed forward neural networks with different number of hidden neurons are used for image data compression. A subimage of size 4X4 pixels forms the input vector of size 16 pixels. The hidden vector, which is the output of the hidden layer whose size is smaller than that of the input vector, represents the compressed form of the image data. The hidden vector is transmitted by a vector quantizer with codebook of 256 codevectors which corresponds to a bit rate of 0.5 bit/pixel. The reconstructed subimage, at the receiver, is obtained from the output layer which consists of 16 neurons. Good reconstructed images are obtained with PSNR of about 30 dB for in-training set image (Lena) and 27 dB for outside-training set image (Boats).

引用

页码：554 / 558

页数：5