Title :
Multiple model encoding of images
Author_Institution :
Media Lab., MIT, Cambridge, MA, USA
Abstract :
Images are fundamentally inhomogeneous and nonlinear, yet most coding has been based on homogeneous processing using linear techniques. This paper describes our progress to develop a framework for nonlinear, multiscale, inhomogeneous coding, and describe the particular research efforts within the MIT Perceptual Computing Section that are beginning to fill out this framework
Keywords :
encoding; image coding; transforms; K-L transform; Massachusetts Institute of Technology; homogeneous processing; image coding; inhomogeneous coding; inhomogeneous images; linear techniques; minimum description length; multiple model encoding; nonlinear images; nonlinear multiscale coding; Frequency estimation; Histograms; Image coding; Image resolution; Laboratories; Nonhomogeneous media; Probability density function; Roads; Statistics; Wavelet coefficients;
Conference_Titel :
Signals, Systems and Computers, 1993. 1993 Conference Record of The Twenty-Seventh Asilomar Conference on
Conference_Location :
Pacific Grove, CA
Print_ISBN :
0-8186-4120-7
DOI :
10.1109/ACSSC.1993.342361
