July 31, 1998 Updated by Ms. Jade Y.S. Hsu
Vol.2 No.1, pp.83-97 (January 1986)

A New Pyramid Architecture for
Bottom-Up Image Analysis

Kuo-Liang Chung
Institute of Information Engineering,
National Taiwan University,
Taipei, Taiwan 107, Republic of China

        In this paper we present a new pyramid architecture, which contains two approaches to reduce the turnaround time dramatically compared with conventional pyramid machines, for bottom-up image analysis. Normalized input approach alleviates the affection of objects' locations and sizes. Self-timed alternate-mode approach utilizes the advantage of picture compactness. As a result, an image-dependent pyramid model is derived. The operation of the new model is illustrated by examples of standard algorithms for interior-based computations (e.g., area) and border-based computations of local properties (e.g., perimeter).


  1. Deterministic Chinese Parsing Using Formal Semantics
  2. A Heuristic Algorithm for PLA Block Folding
  3. To Develop A Relational Data-Knowledge Base System For Solving Decision Problems With Large Data
  4. A New Pyramid Architecture for Bottom-Up Image Analysis
  5. 3-D Object Recognition by Line Features Using Binocular Images