Title :
The treatment of image boundary effects in CMAC networks
Author :
Lu, Hung-Ching ; Tao, Ted
Author_Institution :
Dept. of Electr. Eng., Tatung Univ., Taipei, Taiwan
Abstract :
This paper proposes a novel coding procedure which makes two dimension CMAC networks learn the feature of transmitted image without boundary effects. As a result, the reconstructed image from the proposed CMAC networks gets higher PSNR. Finally, we apply CMAC networks to JPEG compression. Experimental results demonstrate that the presented method can get higher PSNR at lower bit rate after reconstruction.
Keywords :
cerebellar model arithmetic computers; data compression; image coding; image reconstruction; learning (artificial intelligence); variable rate codes; CMAC networks; JPEG compression; PSNR; bit rate; image boundary effect treatment; image coding procedure; image feature learning; image reconstruction; Discrete Fourier transforms; Discrete wavelet transforms; Fast Fourier transforms; Image coding; Image reconstruction; Image storage; Intelligent networks; Neural networks; PSNR; Pulse modulation;
Conference_Titel :
Neural Networks, 2004. Proceedings. 2004 IEEE International Joint Conference on
Print_ISBN :
0-7803-8359-1
DOI :
10.1109/IJCNN.2004.1380043
