In the mobile communication field, some of the video applications boosted the interest of robust methods for video quality assessment. Out of all existing methods, We Preferred, No Reference Video Quality Assessment is the one which is most needed in situations where the handiness of reference video is partially available. Our research interest lies in formulating and melding effective features into one model based on human visualizing characteristics. Our work explores comparative study between Supervised and unsupervised learning methods. Therefore, we implemented support vector regression algorithm as NR-based Video Quality Metric(VQM) for quality estimation with simplified input features. We concluded that our proposed model exhibited sparseness even after dimension reduction for objective scores of SSIM quality metric.

翻译：在移动通信领域，部分视频应用推动了鲁棒视频质量评估方法的研究兴趣。在所有现有方法中，我们更倾向于无参考视频质量评估，该方法在参考视频部分可用的情况下最为需要。我们的研究兴趣在于基于人类视觉特性，将有效特征制定并融合为单一模型。本研究探讨了有监督与无监督学习方法之间的比较。因此，我们采用支持向量回归算法作为基于无参考的视频质量度量，结合简化输入特征进行质量评估。结论表明，即使对SSIM质量度量的客观分数进行降维处理，我们提出的模型仍表现出稀疏性。