Abstract
Keyframe recognition in video is very important for extracting pivotal information from videos. Numerous studies have been successfully carried out on identifying frames with motion objectives as keyframes. The definition of “keyframe” can be quite different for different requirements. In the field of E-commerce, the keyframes of the products videos should be those interested by a customer and help the customer make correct and quick decisions, which is greatly different from the existing studies. Accordingly, here, we first define the key interested frame of commodity video from the viewpoint of user demand. As there are no annotations on the interested frames, we develop a fast and adaptive clustering strategy to cluster the preprocessed videos into several clusters according to the definition and make an annotation. These annotated samples are utilized to train a deep neural network to obtain the features of key interested frames and achieve the goal of recognition. The performance of the proposed algorithm in effectively recognizing the key interested frames is demonstrated by applying it to some commodity videos fetched from the E-commerce platform.
Highlights
Videos have been successfully used in an increasing number of fields due to the development of video technology, including video retrieval [1], recommending interested videos to users in the personalized recommendation [2], recognizing and tracking moving targets based on surveillance videos as pattern recognition [3], and so on
Aiming at the above problems, we propose an algorithm of commodity video keyframe recognition based on adaptive clustering annotation to solve commodity video keyframe extraction
The paper is organized as follows: In Section 2, we provide a review of related work about keyframe extraction, image clustering, and deep neural network algorithm
Summary
Videos have been successfully used in an increasing number of fields due to the development of video technology, including video retrieval [1], recommending interested videos to users in the personalized recommendation [2], recognizing and tracking moving targets based on surveillance videos as pattern recognition [3], and so on. Existing keyframe extraction algorithms have achieved good results in motion target detection, key figure detection, creating video abstracts, and other fields but these algorithms either lack static feature extraction or pay attention to the overall features of the video while ignoring the uniqueness of a single frame or needing prior parameters that greatly limits the application value of keyframe extraction. These studies mainly focused on the movement information in the video and did not consider individual demands.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have