Title :
Image Compression Based On the Inverse Difference Pyramid with BPNN
Author :
Chekashyn, V. ; Hikal, N.A. ; Kountchev, R.K. ; Biletskiy, Yevgen
Author_Institution :
Tech. Univ. of Sofia
Abstract :
The present paper is devoted to development of a new algorithm of lossless image compression. The proposed algorithm is based on the combination of the back propagation learning neural networks (BPNN) and the method of inverse difference pyramid (IDP) decomposition. This algorithm is well suited to be used in progressive image transmission (PIT). The presented algorithm has been applied to grayscale images in this work. The advantage of the underlined method is the adaptation of neural network to the compression and reproduction of the image contents, which minimizes of the total number of pyramid levels and results increasing the restored image quality
Keywords :
backpropagation; data compression; image coding; image colour analysis; image restoration; neural nets; BPNN; back propagation learning neural networks; grayscale images; image compression; image contents reproduction; inverse difference pyramid decomposition; progressive image transmission; restored image quality; Data communication; Data structures; Discrete cosine transforms; Image coding; Image communication; Image resolution; Image storage; Laplace equations; Neural networks; Spatial resolution;
Conference_Titel :
Industrial Electronics, 2006 IEEE International Symposium on
Conference_Location :
Montreal, Que.
Print_ISBN :
1-4244-0496-7
Electronic_ISBN :
1-4244-0497-5
DOI :
10.1109/ISIE.2006.295536
