Image automatic annotation method and device based on decision tree

Abstract

The invention provides an image automatic annotation method and device based on a decision tree. The device comprises an input unit, a pre-processing unit, a segmentation and extraction unit, an annotation probability calculation unit, a spanning tree unit, an inter-word correlation calculation unit and a keyword selection unit. Compared with the prior art, the method of the present invention hasthe advantages that some obtained blurred images are repaired, thus the image semantic automatic annotation technology is applied to a wider scope, the underlying features of the images are more comprehensively extracted, global features and local features are used to reflect the true visual content of the images, the accuracy of image semantics automatic annotation is improved, scale-invariant features of principal component analysis are adopted by the global features, the computational efficiency is improved, especially for high-dimensional images, the unmeasurable nature of massive image sets is solved, an image annotation problem is converted into a classification problem to carry out annotation, and the annotation performance of a traditional model is improved.

Description

technical field [0001] The invention relates to the technical field of image semantic automatic labeling, in particular to a decision tree-based automatic image labeling method and device. Background technique [0002] With the rapid development of Internet technology, millions of new images are growing on the Internet every day. How to quickly and efficiently retrieve target images from massive images according to user needs is the goal of image retrieval systems. Image semantic annotation is a key step in the preparation of image retrieval. Through image semantic annotation, the image retrieval problem can be transformed into a text retrieval problem with mature technology and high efficiency. However, the traditional semantic annotation is to manually describe keywords for each image. In the era of data explosion, this method is obviously time-consuming and inefficient. Semantic automatic annotation based on image content is to use computer to automatically extract vis...

AI Technical Summary

Problems solved by technology

[0003] However, an ideal semantic automatic labeling model requires an ideal training set that can label any image. In order to achieve automatic image labeling as much as possible, the number of images in the training set used is very large, which can be said to be unmeasurable.

In order to obtain more accurate labeling results during the labeling process, it is sometimes necessary to perform multiple calculations on all the images in the training set, including those images that have very low correlation with the image to be labeled, or even images that have no relationship at all, which undoubtedly increases the calculation. The cost, which will have a negative impact on the labeling results

Images