李昆仑,熊婷,张炘,廖频

• 1:南昌大学科学技术学院
• 2:南昌大学信息工程学院

摘要(Abstract)：

针对低质量人脸图像严重影响人脸检测与分类精度的问题,提出一种基于级联SVM的无参考人脸图像质量评价系统。该系统从人脸图像的分类性能出发,使用不同程度的模糊、光照不均和含噪声退化的人脸图像数据集训练级联SVM,并将SVM的输出作为图像质量的评分。仿真测试与实验结果表明,所提出的系统能较好处理各种退化情况,相比于传统的图像质量评估方式能获得更准确的评估分数。

关键词(KeyWords)： 级联SVM;人脸检测;图像识别;质量评价系统;分类性能;噪声退化

Abstract:

Keywords:

基金项目(Foundation): 江西省教育厅科学技术研究项目(GJJ161525;GJJ151510;GJJ151506);; 江西省科技厅研究项目(20161BBE50049)~~

作者(Author): 李昆仑,熊婷,张炘,廖频

DOI: 10.16652/j.issn.1004-373x.2018.24.024

参考文献(References)：

• [1]王涛,王佰玲.非均匀光照条件下的彩色人脸图像增强[J].计算机工程与应用,2017,53(5):164-169.WANG Tao,WANG Bailing. Enhancement method for color face image with non-uniform illumination[J]. Computer engineering and applications,2017,53(5):164-169.
• [2]吕风杰,信科.基于小波域峰态值的无参考噪声图像评价算法[J].计算机工程与应用,2017,53(7):202-205.LüFengjie,XIN Ke. Blind noisy image quality assessment algorithm based on wavelet kurtosis[J]. Computer engineering and applications,2017,53(7):202-205.
• [3]楼申龙,虞中捷.基于FSIM和不同颜色模型的彩色图像评价方法研究[J].电脑知识与技术,2017,13(7):226-228.LOU Shenlong,YU Zhongjie. The study of colored image quality assessment based on FSIM&diverse color models[J]. Computer knowledge and technology,2017,13(7):226-228.
• [4]张文娟,张丽丽,王艳红.基于非局部结构张量的SSIM图像质量评价方法[J].计算机应用研究,2017,34(10):3162-3164.ZHANG Wenjuan,ZHANG Lili,WANG Yanhong. SSIM image quality assessment based on nonlocal structure tensor[J].Application research of computers,2017,34(10):3162-3164.
• [5]李红丽,马耀锋.基于多特征融合和混合核SVM的目标识别方法[J].沈阳工业大学学报,2018,40(4):441-446.LI Hongli,MA Yaofeng. Target recognition method based on multi-feature fusion and hybrid kernel SVM[J]. Journal of Shenyang University of Technology,2018,40(4):441-446.
• [6]李俊峰,方建良,戴文战.基于色彩感知的无参考图像质量评价[J].仪器仪表学报,2015,36(2):339-350.LI Junfeng,FANG Jianliang,DAI Wenzhan. No-reference image quality assessment based on color perception[J]. Chinese journal of scientific instrument,2015,36(2):339-350.
• [7]朱文斌,陈强,杨曦晨.无参考图像质量评价[J].现代电子技术,2015,38(18):81-88.ZHU Wenbin,CHEN Qiang,YANG Xichen. No-reference assessment algorithms for image quality[J]. Modern electronics technique,2015,38(18):81-88.
• [8]边航,汪友生.基于遗传算法和AdaboostSVM的人脸检测算法[J].计算机与数字工程,2017,45(7):1407-1410.BIAN Hang,WANG Yousheng. Face detection based on genetic algorithms and AdaboostSVM algorithm[J]. Computer and digital engineering,2017,45(7):1407-1410.
• [9]朱伟,黄湘鹏,杜瀚宇,等.基于ORBP和级联分类的实时行人检测算法[J].指挥信息系统与技术,2017,8(5):104-108.ZHU Wei,HUANG Xiangpeng,DU Hanyu,et al. Real-time pedestrian detection algorithm based on ORBP and cascade classifier[J]. Command information system and technology,2017,8(5):104-108.
• [10]李振雨,王好臣,王功亮,等.基于级联Adaboost和神经网络主元分析算法的人脸检测系统[J].科学技术与工程,2018,18(1):280-286.LI Zhenyu,WANG Haochen,WANG Gongliang,et al. Face detection system based on cascade′s algorithm of Adaboost and principal component analysis[J]. Science technology and engineering,2018,18(1):280-286.
• [11]翟社平,李炀,马蒙雨,等.基于LBP和SVM的人脸检测[J].计算机技术与发展,2017,27(9):44-47.ZHAI Sheping,LI Yang,MA Mengyu,et al. Face detection based on LBP and SVM[J]. Computer technology and development,2017,27(9):44-47.
• [12]黄超,薄华.基于卷积神经网络结合SVM的人脸识别研究[J].微型机与应用,2017,36(15):56-58.HUANG Chao,BO Hua. Study on face recognition based on CNN and SVM[J]. Microcomputer&its applications,2017,36(15):56-58.