Video quality assessment using objective parameters based on image segmentation

被引：19

作者：

Pessoa, A ^{[1
]}

Falcao, A ^{[1
]}

Nishihara, R ^{[1
]}

Silva, A ^{[1
]}

Lotufo, R ^{[1
]}

机构：

[1] State Univ Campinas, Campinas, SP, Brazil

来源：

SMPTE JOURNAL | 1999年 / 108卷 / 12期

关键词：

D O I：

10.5594/J04308

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

This work presents a new methodology for video quality assessment using objective parameters based on image segmentation. The method is applied to a set of natural scenes and MPEG-2 video codecs, An image segmentation algorithm divides the scenes into three regions: plane, edges, and texture; and assigns a set of objective parameters to each region, A perceptual-based model is defined by computing the relationship between objective measures and results of subjective assessment tests. Thereafter the model allows subjective rating prediction without human input. The work shows that region-based objective measurements provide more accurate predictions as compared to global measurements.

引用

页码：865 / 872

页数：8