基于深度学习的视频检索方法研究

Research of Video Retrieval Method Based on Deep Learning

深度学习由于其强大的特征表示能力在图像处理、语音识别、推荐系统能领域取得了重大进展。论文提出了一种基于深度学习的针对视频对特定人进行检索的方法,该方法综合使用了MTCNN的人脸检测与对齐以及FaceNet的人脸识别功能,同时论文针对视频连续性的特点,对检索结果进行了特殊处理,实验结果表明论文方法具有较高的准确率和较快的速度。

Deep learning has made significant progress in the fields of image processing,speech recognition,and recommen⁃dation system energy due to its powerful feature representation capabilities.In this paper,a deep learning-based method for video retrieval of specific people is presented.This method uses MTCNN's face detection and alignment and FaceNet's face recognition function.At the same time,according to the characteristics of video continuity,the retrieval results are specially processed.The ex⁃perimental results show that our method has high accuracy and speed.