论文信息 - SIGMA: A Framework for Image Understanding - Integration of Bottom-Up and Top-Down Analysis

SIGMA: A Framework for Image Understanding - Integration of Bottom-Up and Top-Down Analysis

The framework and control structure of an image understanding system SIGMA arc presented. SIGMA consists of three experts: Gelmetric Reasoning Expert (GRE) for spatial reasoning. Model Selection Expert (MSE) for appearance model selection, and Low level Vision Expert (LIVE) for knowledge-based picture processing. Tills paper mainly describes the control mechanism for the spatial reasoning by GRE, where bottom-up and top-down analyses are integrated into a unified reasoning process.

Takashi Matsuyama | Vincent Shang-Shouq Hwang

[1] William S. Havens,et al. Representing Knowledge of the Visual World , 1983, Computer.

[2] John K. Tsotsos. Temporal Event Recognition: An Application to Left Ventricular Performance , 1981, IJCAI.

[3] Thomas O. Binford,et al. Survey of Model-Based Image Analysis Systems , 1982 .

[4] Makoto Nagao,et al. A Structural Analysis of Complex Aerial Photographs , 1980, Advanced Applications in Pattern Recognition.

[5] Marvin Minsky,et al. A framework for representing knowledge , 1974 .

[6] Peter Gilman Selfridge,et al. Reasoning about success and failure in aerial image understanding , 1982 .