QQ客服 官方微博 反馈留言

	RANK LEARNING ON TRAINING SET SELECTION AND IMAGE QUALITY ASSESSMENT
	Xu, Long ; Lin, Weisi ; Li, Jia ; Wang, Xu ; Yan, Yihua ; Fang, Yuming
	2014
关键词	Rank learning image quality assessment gradient decedent optimization MEAN SQUARED ERROR STATISTICS JPEG2000
英文摘要	Machine learning (ML) techniques are widely used in recent no-reference visual quality assessment (NR-VQA) metrics by training on subjective image quality databases. In these metrics, the optimization function is constructed based on L-2 norm of the distance between subjective image quality and predicted image quality. There are two problems in these L-2 norm based methods: (1) human's opinion on subjective image quality rating is not reliable at fine-scale level. A small difference between subjective image qualities represented by mean opinion scores (MOSs) of two images may not truly reflect the real quality difference between these two images, but acts as noise. The optimization process should avoid such noise. (2) Generally, human's opinion on pairwise comparison (PC) for image quality is more reliable and believable than MOS. The importance of PC is ignored during the optimization process of existing ML-based studies, which are designed based on the numerical rating system. In this paper, we introduce image quality ranking concept to establish a new optimization objective instead of L-2 norm optimization, and then a novel NR-VQA is constructed based on ranking learning. The proposed metric firstly suggests a reasonable training set for ML, which is ignored by existing ML-based NR-VQA. The ranking theory is adopted to build optimization function, which reflects the properties of PC over the numerical ranting system used by traditional NR-VQA. By ignoring the small difference between MOSs from two images during the optimization process, the proposed ranking-based NR-VQA can also well address the first problem from the existing related metrics. Experimental results show that the proposed ranking-based NR-VQA can obtain better performance over the state-of-the-art NR-VQA approaches.; EI; CPCI-S(ISTP); xulong@ntu.edu.sg; wslin@ntu.edu.sg; jia.li@pku.edu.cn; wangxu.cise@gmail.com; yyh@nao.cas.cn; ymfang@ntu.edu.sg; Septmber; 2014-September
语种	中文
出处	2014 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO (ICME)
DOI标识	10.1109/ICME.2014.6890291
内容类型	其他
源URL	[http://ir.pku.edu.cn/handle/20.500.11897/423863]
专题	信息科学技术学院
推荐引用方式 GB/T 7714	Xu, Long,Lin, Weisi,Li, Jia,et al. RANK LEARNING ON TRAINING SET SELECTION AND IMAGE QUALITY ASSESSMENT. 2014-01-01.

个性服务

查看访问统计

相关权益政策

暂无数据

收藏/分享

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。