设为首页收藏本站

VALSE

VALSE 首页 活动通知 好文作者面授招 查看内容

20150826-27 张林:基于自然场景统计模型的无参考图像质量评价

2015-8-23 16:53| 发布者: 彭玺ASTAR| 查看: 6320| 评论: 0

摘要: 【15-27期VALSE Webinar活动】报告嘉宾1:张林(同济大学)主持人:董伟生(西安电子科技大学)报告题目:基于自然场景统计模型的无参考图像质量评价文章信息: Lin Zhang, Lei Zhang, and Alan C. Bovik, "A featur ...

【15-27期VALSE Webinar活动】

报告嘉宾1张林(同济大学)
主持人董伟生(西安电子科技大学)
报告题目:基于自然场景统计模型的无参考图像质量评价 [Slides]
文章信息:
[1] Lin Zhang, Lei Zhang, and Alan C. Bovik, "A feature-enriched completely blind image quality evaluator", IEEE Trans. Image Processing, vol. 24, no. 8, pp. 2579-2591, 2015
[2] Lin Zhang, Ying Shen, and Hongyu Li, "VSI: A visual saliency induced index for perceptual image quality assessment", IEEE Trans. Image Processing, vol. 23, no. 10, pp. 4270-4281, 2014
[3] Lin Zhang, Lei Zhang, Xuanqin Mou, and David Zhang, "FSIM: A feature similarity index for image quality assessment", IEEE Trans. Image Processing, vol. 20, no. 8, pp. 2378-2386, 2011
报告摘要:Existing blind image quality assessment (BIQA) methods are mostly opinion-aware. Such opinion-aware methods, however, require a large amount of training samples with associated human subjective scores and of a variety of distortion types. The BIQA models learned by opinion-aware methods often have weak generalization capability, hereby limiting their usability in practice. By comparison, opinion-unaware methods do not need human subjective scores for training, and thus have greater potential for good generalization capability. Unfortunately, thus far no opinion-unaware BIQA method has shown consistently better quality prediction accuracy than opinion-aware methods. Here we aim to develop an opinion-unaware BIQA method that can compete with, and perhaps outperform existing opinion-aware methods. By integrating natural image statistics features derived from multiple cues, we learn a multivariate Gaussian model of image patches from a collection of pristine natural images. Using the learned multivariate Gaussian model, a Bhattacharyya-like distance is used to measure the quality of each image patch, then an overall quality score is obtained by average pooling. The proposed BIQA method does not need any distorted sample images nor subjective quality scores for training, yet extensive experiments demonstrate its superior quality-prediction performance to state-of-the-art opinion-aware BIQA methods.
报告人简介:张林博士现为同济大学软件学院副教授。他曾于2003年和2006年在上海交通大学计算机科学与技术系分别获得学士和硕士学位。之后曾先后供职于Microsoft和Autodesk公司。2008年3月至香港理工大学攻读博士学位,导师为张磊教授。2011年8月博士毕业后,加入同济大学。主要研究兴趣包括生物特征识别和多媒体质量评价。他以第一作者身份已在IEEE TPAMI、IEEE TIP、PR、IVC等期刊上发表论文12篇。根据Google Scholar统计,截至目前,其所发表论文总的被引用次数为1558次;其中,2篇论文入选ESI高被引论文。其论文“FSIM: A feature similarity index for image quality assessment, IEEE Trans. Image Processing, 20 (8) 2378-2386, 2011”为IEEE TIP自2011年以来所有发表论文中被引用次数最高的论文。其论文“Online finger-knuckle-print verification for personal authentication, Pattern Recognition, 43 (7) 2560-2571, 2010”曾获Pattern Recognition杂志最佳论文提名。其论文“3D ear identification using LC-KSVD and local histograms of surface types”获得ICME2015最佳论文提名。他于2013年入选上海市浦江人才计划。

最新评论

Archiver|手机版|小黑屋|Vision And Learning SEminar    

GMT+8, 2020-9-26 22:38 , Processed in 0.028516 second(s), 19 queries .

Powered by Discuz! X3.2

© 2001-2013 Comsenz Inc.

返回顶部