基于视频引导模型更新的视频肤色增强方法

Video Skin-Color Enhancement Method Based on Video-Guided Model Updates

在视频的采集和跨媒体再现过程中,相机的色域限制往往会导致获取的图像色彩失真。其中肤色作为人眼最敏感的色彩之一,肤色失真可能会降低观众的视觉体验。肤色增强是一种针对图像或视频中人类肤色的处理技术,通过对失真的肤色进行调整,达到提高显示质量的目的。尤其是在视频处理领域,在提高肤色模型自适应性的同时,还需要考虑算法的实时性与计算工作量,因此,提出一种面向实时视频处理的自适应肤色增强方法。利用镜头边界来引导肤色模型更新,以此降低模型更新的计算工作量;其次,建立一种根据镜头边界更新的动态肤色模型进行皮肤检测;最后,基于主观实验建立了偏好肤色模型,并且实现了针对不同种族的肤色增强。与现有方法相比,所提方法在主观评价实验中取得了更高的平均主观分值。实验结果表明,所提方法可以显著降低模型更新带来的计算工作量,同时实现有针对性的肤色增强。

During the acquisition and cross-media reproduction of videos,colors can be distorted because the color gamut of the camera is limited and may differ from the color gamut of the display device.Skin color is among the most sensitive colors to the human eye.Therefore,skin-color distortion can deteriorate viewers' video experience.Skin-color enhancement is a processing technology that adjusts a distorted skin color to improve the display quality.Particularly in video processing,the self-adaptability of a skin-color model must be improved while considering the real-time performance and computational load of the algorithms.For these purposes,the present paper proposes an adaptive skin-color enhancement method for real-time video processing.The update of the skin-color model is guided by shot boundaries,which can reduce the computational load of updating.Second,a dynamic skin-color model updated with the shot boundary is built for skin detection.Finally,the preferred skin-color model and skin-color enhancements for different races are achieved through subjective experiments.The proposed method achieved higher mean opinion scores than the existing methods in subjective evaluation experiments.In addition to achieving the targeted skin-color enhancement,the proposed method significantly reduced the computational load of model update.