Undesirable image detecting method based on connotative theme analysis

Abstract

The invention discloses an undesirable image detecting method based on connotative theme analysis, which is substantially used for solving the problem of wrong judgment on normal images resulting from semantic information consideration failure in the present undesirable information detecting method. The scheme is as follows: extracting a skin region of an image by a double-blending Gaussian model; generating a codebook base containing distinguishing features in the skin region by a word bag model, and representing each training image to a group of word co-occurrence vectors with weights via aword frequency-inverse identification file frequency method; forming all co-occurrence vectors to a co-occurrence matrix, performing LDA model creation on the co-occurrence matrix to obtain the themeof the image; inputting the mixed theme of the training image in a BP neural network to train an undesirable image classifier; and obtaining the theme of an image to be measured, inputting the theme to the undesirable image classifier, and judging whether the theme is an undesirable image so as to finish the undesirable image detection. As shown in the test, the invention can be used for better distinguish the undesirable images and the normal images, so that the invention can be used for filtering the erotic information in the images.

Description

technical field [0001] The invention belongs to the intersecting field of computer vision and pattern recognition, and in particular relates to a semantic classification method of bad images based on implicit theme analysis, which can be used to filter pornographic information in images. Background technique [0002] With the vigorous rise of the Internet in the 1990s, all kinds of information on the Internet have grown and spread rapidly. Especially with the advent of the 3G era and the concept of converged networks, images are rapidly disseminated in the field of instant messaging on the basis of multimedia messages and mobile video streams, which contain a large amount of obscene and pornographic information. The dissemination of a large amount of bad information has adverse effects on people's physical and mental health. Therefore, it is of far-reaching significance to propose an advanced method for filtering bad information. For bad information filtering, how to correc...

AI Technical Summary

Problems solved by technology

[0009] (1) The extracted human skin color area often contains interference information such as hair, which is not conducive to subsequent bad feature extraction

[0010] (2) The texture of the skin color area of ​​the image is relatively similar, and the discriminative bad image features are often submerged in a large number of normal skin color texture features, so that the discriminative features cannot be effectively used in bad image classification tasks

[0011] (3) The connection between features and image semantics is disconnected, and the lack of image semantic information description leads to a low correct detection rate

Images