Statistical split and polynomial merge algorithm for image representation

Seoung-Jun Oh; Keun-Heum Park

doi:10.1117/12.206696

21 April 1995 Statistical split and polynomial merge algorithm for image representation

Seoung-Jun Oh, Keun-Heum Park

Proceedings Volume 2501, Visual Communications and Image Processing '95; (1995) https://doi.org/10.1117/12.206696
Event: Visual Communications and Image Processing '95, 1995, Taipei, Taiwan

Abstract

Since polynomials fit the geometrical forms of images harmoniously and well represent slowly varying surfaces in images, there were many split and merge algorithms which used a polynomial function to represent each homogeneous region. Even though very low-bit rate can be achieved using their algorithms, it takes too much time for both split process and merging process. Furthermore, the splitted result is not quite well matched to HVS, either. In this paper, a new split and merge algorithm is designed. In this algorithm the split process uses a statistical hypothesis test called ShortCut method as a measurement of region homogeneity, and the merge process uses a polynomial function. The computation time for the split process can be significantly reduced using the new algorithm, and the new scheme reflects HVS more than any other scheme. To justify the algorithm proposed here, it is compared with other algorithms including Kunt's algorithm.

Citation Download Citation

Seoung-Jun Oh and Keun-Heum Park "Statistical split and polynomial merge algorithm for image representation", Proc. SPIE 2501, Visual Communications and Image Processing '95, (21 April 1995); https://doi.org/10.1117/12.206696

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available