Saliency Detection via the Improved Hierarchical Principal Component Analysis Method

被引:62
作者
Chen, Yuantao [1 ,2 ]
Tao, Jiajun [1 ,2 ]
Zhang, Qian [3 ]
Yang, Kai [3 ]
Chen, Xi [1 ,2 ]
Xiong, Jie [4 ]
Xia, Runlong [5 ]
Xie, Jingbo [5 ]
机构
[1] Changsha Univ Sci & Technol, Sch Comp & Commun Engn, Changsha 410114, Peoples R China
[2] Changsha Univ Sci & Technol, Hunan Prov Key Lab Intelligent Proc Big Data Tran, Changsha 410114, Peoples R China
[3] Hunan ZOOMLION Intelligent Technol Corp Ltd, Dept Elect Prod, Changsha 410005, Peoples R China
[4] Yangtze Univ, Elect & Informat Sch, Jingzhou 434023, Peoples R China
[5] Hunan Inst Sci & Tech Informat, Changsha 410001, Peoples R China
基金
中国国家自然科学基金;
关键词
VISUAL-ATTENTION;
D O I
10.1155/2020/8822777
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Aiming at the problems of intensive background noise, low accuracy, and high computational complexity of the current significant object detection methods, the visual saliency detection algorithm based on Hierarchical Principal Component Analysis (HPCA) has been proposed in the paper. Firstly, the original RGB image has been converted to a grayscale image, and the original grayscale image has been divided into eight layers by the bit surface stratification technique. Each image layer contains significant object information matching the layer image features. Secondly, taking the color structure of the original image as the reference image, the grayscale image is reassigned by the grayscale color conversion method, so that the layered image not only reflects the original structural features but also effectively preserves the color feature of the original image. Thirdly, the Principal Component Analysis (PCA) has been performed on the layered image to obtain the structural difference characteristics and color difference characteristics of each layer of the image in the principal component direction. Fourthly, two features are integrated to get the saliency map with high robustness and to further refine our results; the known priors have been incorporated on image organization, which can place the subject of the photograph near the center of the image. Finally, the entropy calculation has been used to determine the optimal image from the layered saliency map; the optimal map has the least background information and most prominently saliency objects than others. The object detection results of the proposed model are closer to the ground truth and take advantages of performance parameters including precision rate (PRE), recall rate (REC), and F-measure (FME). The HPCA model's conclusion can obviously reduce the interference of redundant information and effectively separate the saliency object from the background. At the same time, it had more improved detection accuracy than others.
引用
收藏
页数:12
相关论文
共 31 条
[1]  
Achanta R, 2009, PROC CVPR IEEE, P1597, DOI 10.1109/CVPRW.2009.5206596
[2]   A novel online incremental and decremental learning algorithm based on variable support vector machine [J].
Chen, Yuantao ;
Xiong, Jie ;
Xu, Weihong ;
Zuo, Jingwen .
CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS, 2019, 22 (Suppl 3) :S7435-S7445
[3]   RETRACTED: Multiscale fast correlation filtering tracking algorithm based on a feature fusion model (Retracted article. See vol. 34, 2022) [J].
Chen, Yuantao ;
Wang, Jin ;
Liu, Songjie ;
Chen, Xi ;
Xiong, Jie ;
Xie, Jingbo ;
Yang, Kai .
CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE, 2021, 33 (15)
[4]   RETRACTED: The visual object tracking algorithm research based on adaptive combination kernel (Retracted Article) [J].
Chen, Yuantao ;
Wang, Jin ;
Xia, Runlong ;
Zhang, Qian ;
Cao, Zhouhong ;
Yang, Kai .
JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING, 2019, 10 (12) :4855-4867
[5]   RETRACTED: Single-Image Super-Resolution Algorithm Based on Structural Self-Similarity and Deformation Block Features (Retracted Article) [J].
Chen, Yuantao ;
Wang, Jin ;
Chen, Xi ;
Zhu, Mingwei ;
Yang, Kai ;
Wang, Zhi ;
Xia, Runlong .
IEEE ACCESS, 2019, 7 :58791-58801
[6]   Global Contrast Based Salient Region Detection [J].
Cheng, Ming-Ming ;
Mitra, Niloy J. ;
Huang, Xiaolei ;
Torr, Philip H. S. ;
Hu, Shi-Min .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2015, 37 (03) :569-582
[7]   Histograms of oriented gradients for human detection [J].
Dalal, N ;
Triggs, B .
2005 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOL 1, PROCEEDINGS, 2005, :886-893
[8]   Visual Attention Modeling for Stereoscopic Video: A Benchmark and Computational Model [J].
Fang, Yuming ;
Zhang, Chi ;
Li, Jing ;
Lei, Jianjun ;
Da Silva, Matthieu Perreira ;
Le Callet, Patrick .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2017, 26 (10) :4684-4696
[9]   Secure Data Query Framework for Cloud and Fog Computing [J].
Gu, Ke ;
Wu, Na ;
Yin, Bo ;
Jia, Weijia .
IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT, 2020, 17 (01) :332-345
[10]   Image Signature: Highlighting Sparse Salient Regions [J].
Hou, Xiaodi ;
Harel, Jonathan ;
Koch, Christof .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2012, 34 (01) :194-201