Title :
Structural compression and reconstruction of static image by ideal diode retina network
Author :
Cheng, Gui-Xin ; Shimizu, Naoluko ; Tanaka, Mamoru
Author_Institution :
Dept. of Electr. & Electron. Eng., Sophia Univ., Tokyo, Japan
Abstract :
An image structural compression method is proposed. In this method, an original image as link currents is input into the links of a graph whose node currents are transmitted into a reconstruction side. At the reconstruction side, the structural compressed image is reconstructed by using an ideal diode retina network. The ideal diode retina network reconstructs the original image such that the mean squared error between the original image and the reconstructed image is minimized
Keywords :
Gaussian distribution; data compression; image coding; image reconstruction; neural nets; ideal diode retina network; link currents; mean squared error; node currents; original image; static image reconstruction; structural compression; Circuits; Diodes; Gaussian distribution; Image coding; Image edge detection; Image reconstruction; Neural networks; Neurons; Retina; Unified modeling language;
Conference_Titel :
Circuits and Systems, 1993., ISCAS '93, 1993 IEEE International Symposium on
Conference_Location :
Chicago, IL
Print_ISBN :
0-7803-1281-3
DOI :
10.1109/ISCAS.1993.394338
