Automatic video annotation method based on automatic classification and keyword marking

Abstract

The invention discloses an automatic video annotation method based on automatic classification and keyword marking. The automatic video annotation method comprises the following steps of: S1, carrying out preprocessing on a video classification feature; S2, extracting the global feature and the local feature of a video, wherein the global feature is used for training an SVM (Support Vector Machine) model to enable the SVM model to identify different types; and the local feature is used for establishing a multi-feature index model with multiple features which correspond to keywords; and S3, for un-annotated videos from a user, extracting the global feature and the local feature and then enabling the SVM model to identify specific types of the videos by adopting the global feature; and retrieving relevant keywords in the multi-feature index model for annotating by using the local feature; and S4, ordering an annotation result according to a certain weight and then returning the annotation result to the user. According to the automatic video annotation method, the marking performance of the video is improved.

Description

technical field [0001] The invention relates to the technical field of video recognition, in particular to an automatic video annotation method based on automatic classification and keyword labeling. Background technique [0002] With the advancement of science and technology, especially the development and promotion of multimedia digital technology, the reduction of storage costs, the increase of network transmission bandwidth, the improvement of computer processing speed, and the popularization of high-performance computing environments, the objects processed by modern information retrieval and scale have changed a lot. The rapid expansion of multimedia information containing various types of data such as text, images, audio, and video has gradually become the mainstream of information, and has had an important impact on people's lives and social development. Multimedia information has its own characteristics. On the one hand, it has a large amount of information. Seeing ...

AI Technical Summary

Problems solved by technology

Although these "contents" can better express video information, this retrieval method needs to search by comparing these high-dimensional feature information, which consumes a lot of time and resources, which is unacceptable to general network users and is also the current reality. stage is not feasible, so the video retrieval provided by major websites today, such as Google, MSN, YouTube, Baidu, etc., all rely on the description of the text metadata of the video for retrieval

Their search engine cannot analyze every picture in the video like content-based retrieval, let alone be accurate to every pixel, so they cannot search for videos that have not been annotated

Images