Digital image automatic labeling method based on uncertainty analysis

Abstract

A digital image automatic labeling method based on uncertainty analysis, including the steps of extracting image features based on a deep convolutional neural network, constructing an image automaticlabeling system based on a variable precision neighborhood rough set, and labeling unlabeled images. The method includes the following steps: collecting the image data and labeling to obtain a training set, and extracting a feature vector of the image through the deep convolutional neural network; obtaining a classification model based on the neighborhood estimation class conditional probability density; in prediction, extracting image features, and estimating the position of the image to be classified by using upper and lower approximation concepts of the rough set; directly judging the membership of the labels for the images located in positive and negative domains, and judging the images in the boundary domain by using a Bayesian decision rule. According to the digital image automatic labeling method based on uncertainty analysis, the position of images to be labeled in the sample space are estimated by introducing upper and lower approximation concepts of the rough set, the error prediction rate of the irrelevant labels is reduced, and the problem of uncertainty existing between the underlying image feature and the high level semantics in image automatic labeling is solved.

Description

technical field [0001] The invention relates to an automatic labeling method for digital images based on uncertainty analysis, which belongs to the technical field of computer image processing. Background technique [0002] With the rapid development of computer technology and the popularity of multimedia applications and social networks, multimedia data on the Internet has grown exponentially. Massive data brings new opportunities and challenges to multimedia application research, especially image-based application research. In order to dig out the required images from the massive image data, it is necessary to have an effective image retrieval mechanism. Automatic image annotation technology allows computers to automatically add semantic tags that can reflect image content to unlabeled images, which is the key to image retrieval. It tries to establish a mapping relationship between the high-level semantic information of the image and the low-level visual features, automa...

AI Technical Summary

Problems solved by technology

In addition, due to the multi-label feature of image annotation, some scholars regard it as a multi-label learning problem.

However, there are some defects in the existing methods: First, the underlying features of the image cannot fully reflect and match the user's retrieval intention

Finally, existing algorithms ignore the impact of limited training samples, which make it impossible to accurately estimate the distribution of each class

These problems arise mainly because of the uncertainty in the mapping process from the visual feature space to the semantic concept space

Images