Method for constructing prototype vector and reconstructing sequence parameter based on semantic information in image comprehension

Abstract

The invention provides a semantic-based information prototype vector composition and order parameter reconstruction method in image understanding. The method comprises the following steps: 1. the prototype vector representation of scene and target semantic information; 2. the structural representation of scene and target prototype vectors; 3. the reduction treatment of the scene and target prototype vectors; and 4. the reconstruction of scene and target order parameters. The method is based on the synergetics and the synergetic pattern recognition principles, extracts and reconstructs the features of the scene and the target in an image and carries out the feature description which is added by semantic information of the scene and the target in the scene to achieve the purpose of recognizing the image, the computational complexity is low, the study ability is strong, the recognition efficiency is high and the algorithm robustness is stronger.

Description

technical field [0001] The invention relates to the fields of image comprehension, computer vision and synergy, in particular to a method for constructing prototype vectors and order parameter reconstruction based on semantic information in image comprehension. Background technique [0002] The intuitive task of image understanding is to use the computer to model, calculate, analyze and reason the input scene and its target area, form a complete output process of simple text or image graphical marking, and let the computer recognize and judge what objects are in the scene. In what position, what is the relationship between the targets, etc., to solve the basic "what-where" problem, and the information representation method of the scene and the target is the premise and basis for studying various algorithms. In recent years, computer vision technology has developed rapidly. For the learning and discrimination methods and algorithms of endless classification ideas, the cogniti...

AI Technical Summary

Problems solved by technology

The rigidity of the rules leads to its own limitations. The number of rules grows exponentially with the scale of semantic information, and its storage and processing capabilities are NP problems.

[0004] In short, the existing image understanding methods are constrained by the storage and representation of scene and object information, and have shortcomings such as high computational complexity, weak self-learning ability, weak robustness, slow convergence, etc., especially the lack of semantic information and its The structural description of the relationship cannot form effective prior knowledge to guide the computer to recognize and understand the scene and its goals reasonably and accurately

Images