Skip to main content

A Knowledge-Based System for Image Understanding

Tjahjadi T & Henson R

Proc. IEE 3rd Int. Conf. on Image Processing and its Applications, 1989, 88-92


This paper reports the development of a model for image understanding which takes as its input the basic transactions involved in image enhancement and image encodement, and generates as its output recommendations as to the best approach or set of processes to analyse an image. The paper examines the broad area of visual processing, and utilises the study of human visual information processing as a starting point for the model. Inevitably, this approach draws away from the more statistical/mathematical algorithmic methods of image processing towards the fundamental aspects of psychological study. Any algorithmic work will entail the utilisation of biological mechanisms in what might be termed a goal directed biological algorithmic solution. In this respect, the paper takes a far-sighted view of image processing, stressing the need to develop strong theory behind the processing of visual information in order to perform the complex operation of image understanding.