MEF融合HFF的戏剧视频关键情节自动提取

Automatic Highlights Extraction for Key Plot of Drama Video Based on Fusion of MEF and HFF

为了更好地从戏剧视频提取关键情节,提出了一种基于音乐情感特征(MEF)融合人脸特征(HFF)的自动提取方法。首先,利用基于音频指纹技术的二级音乐情感识别方法进行音频识别,并利用人脸特征进行视频识别;然后,利用音频和视频识别得到的各元素获取关键情节值,从而提取关键情节;最后,提出了一种量化评估方法评估关键情节提取方法的一致性。在四个戏剧视频上的评估实验验证了该方法的有效性及可靠性,相比其他几种较新的提取模型,该方法提取效果更好。

Order to extract key plot of the drama videos, an automatic extraction for key plot based on fusion of music emotion features （MEF） and human face features （HFF） is proposed. Firstly, a two music-based emotion recognition method based on audio fingerprinting technology is used to do audio recognition, human face features is used to do video recognition. Then, the elements of audio and video identification are used to get access to key plot value to extract key plot. Finally, a quantitative assessment method is proposed to estimate the consistency of proposed method. The validity and reliability of the assessment has been verified by the quantitative evaluation on the four drama videos method, proposed method has better results than several other new extraction methods.