Image engineering intelligent interpretation method

Abstract

The invention relates to the field of image information processing and particularly relates to an image engineering intelligent interpretation method. The method comprises steps of obtaining multi-source image data according to a preset data input standard; extracting image information of the obtained multi-source image data according to a preset image information extraction standard; automatically screening expert interpretation knowledge which meets preset conditions through automatically-allocated task processing nodes based on the extracted image information, and determining the most suitable expert interpretation knowledge; interpreting the determined most suitable expert interpretation knowledge, to obtain image interpretation achievement data which accords with a preset rule set; and performing statistical analysis of the image interpretation achievement data, and outputting the achievement data according to a preset achievement output standard. The invention solves problems that the traditional labor visual interpretation has low efficiency, and the common intelligent interpretation is low in precision and non-standard in result, and achieves standardization and engineering of image interpretation.

Description

technical field [0001] The invention relates to the field of image information processing, in particular to an image engineering intelligent interpretation method. Background technique [0002] Image interpretation, that is, the process of obtaining target information from images, mainly has two methods. One is visual interpretation, also known as visual interpretation or visual interpretation. The distribution law and the experience of the interpreter deduce the type of image from the brightness, tone, position, time, texture, shadow, structure and other characteristics of the image; the second is the automatic interpretation of the computer, which uses the computer system as the supporting environment, Using the combination of pattern recognition technology and artificial intelligence technology, according to various image features (color, shape, texture and spatial position) of the target object in the image, combined with the interpretation experience and imaging rules o...

AI Technical Summary

Problems solved by technology

[0003] The traditional visual interpretation method mainly relies on manual drawing and interpretation, which is time-consuming and laborious, and the operator's degree of cognition of the object determines the quality of the interpretation results, which is not efficient and cannot meet the needs of engineering; the current popular image 1. Although the information extraction software provides functions such as supervised classification and unsupervised classification, its effect in the actual application of classification of objects is not ideal, and the accuracy of interpretation work is not accurate and the results are not standard

Images