Image understanding system based on layered temporal memory algorithm and image understanding method thereof

Abstract

The invention relates to an image understanding (IU) system based on a layered temporal memory algorithm and an IU method thereof. The IU system consists of a layered temporal memory network training module, a layered temporal memory network database and an IU module. Besides, the IU method comprises the following steps: constructing a training image set P; training layered temporal memory networks by utilizing the training image set P; storing the trained layered temporal memory networks into the layered temporal memory network database; and carrying out understanding on a target image by utilizing all the layered temporal memory networks stored in the layered temporal memory network database. According to the invention, a novel time mode set learning method and a novel database technology are applied to rapidly convert several image content attributes into natural semantic description, thereby realizing deep understanding on the image. Compared with a traditional IU method, the provided IU method has advantages of simpleness, high practicability and flexibility.

Description

technical field [0001] The present invention relates to image semantic understanding, especially an image understanding system and image understanding method based on hierarchical temporal memory algorithm, specifically refers to an image based on hierarchical temporal memory algorithm, which recognizes multiple attributes of an image and adds semantics according to the recognition result Labeling, a method of image understanding that converts image content information into natural language descriptions. Background technique [0002] Image Understanding (IU) is the semantic understanding of images. It takes the image as the object, knowledge as the core, and studies what objects are in the image, the relationship between the objects, what scene the image is, and how to apply the scene. [0003] Image understanding belongs to one of the research contents of digital image processing and belongs to high-level operation. The focus is to further study the nature and relationshi...

AI Technical Summary

Problems solved by technology

[0004] At present, the commonly used image understanding methods mainly use some image processing algorithms to extract the features of the image, and then use image recognition algorithms and reasoning algorithms to classify and identify the extracted features. Commonly used image processing algorithms include fast Fourier transform, edge extraction, etc. Commonly used image recognition and reasoning algorithms include Support Vector Machines (SVM), Hidden Markov Models (HMM) and moment feature Zernike moments, etc. From the perspective of algorithm implementation, currently commonly used image processing algorithms There is a common disadvantage of large amount of calculation. The existing two-dimensional Markov model in the hidden Markov model has the disadvantages of strong local dependence, complicated calculation process and difficult programming. The image recognition effect of the moment feature Zernike moment is easily affected by the parameter The influence of identifying volatility is large

Images