基于深度学习的显著性检测方法模型——SCS

doi:10.3969/j.issn.10062475.2018.04.010

摘要/Abstract

摘要： 提出一种基于深度学习的图像显著性区域检测方法，该方法对2种视觉注意机制所涉及的低级对比特征和高级语义特征分别进行提取，并结合2类特征进行模型训练最终得到基于分类思想的图像显著性区域检测模型——SCS检测模型。通过对比实验得出：该方法训练得到的检测模型在检测准确度上具有显著的优势。

关键词: 显著性, 对比特征, 语义特征, 分类, 检测模型

Abstract: In this paper, we propose a method of saliency detection based on deep learning. This method extracts the lowlevel contrast features and highlevel semantic features involved in the two visual attention mechanisms, and combines both of them to obtain a classificationbased saliency detection model SCS. Through the comparison experiment, it is concluded that the proposed detection model has significant advantages in the accuracy of saliency detection.

Key words: saliency, contrast feature, semantic feature, classification, detection model

中图分类号:

TP391

张洪涛，路红英，刘腾飞，张玲玉，张晓明. 基于深度学习的显著性检测方法模型——SCS[J]. 计算机与现代化, doi: 10.3969/j.issn.10062475.2018.04.010.

ZHANG Hongtao, LU Hongying, LIU Tengfei, ZHANG Lingyu, ZHANG Xiaoming. SCS: A Model of Saliency Detection Based on Deep Learning[J]. Computer and Modernization, doi: 10.3969/j.issn.10062475.2018.04.010.

参考文献

［1］ Chen Liqun, Xie Xing, Fan Xin, et al. A visual attention model for adapting images on small displays［J］. Multimedia Systems, 2003,9(4):353364.
［2］ Hou Xiaodi, Zhang Liqing. Saliency detection: A spectral residual approach［C］// Proceedings of the 2007 IEEE Conference on Computer Vision and Pattern Recognition. 2007, doi: 10.1109/CVPR.2007.383267.
［3］ Christopoulos C, Skodras A, Ebrahimi T. The JPEG2000 still image coding system: An overview［J］. IEEE Transactions on Consumer Electronics, 2000,46(4):11031127.
［4］〖JP3〗Ko B C, Nam J Y. Automatic objectofinterest segmentation from natural images［C］// Proceedings of the 18th International Conference on Pattern Recognition. 2006,4:4548. 
［5］〖JP3〗Chen Tao, Cheng Mingming, Tan Ping, et al. Sketch2Photo: Internet image montage［J］. ACM Transactions on Graphics, 2009,28(5): Article No. 124. 
［6］ Perazzi F, Krhenbühl P, Pritch Y, et al. Saliency filters: Contrast based filtering for salient region detection［C］// Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition. 2012:733740.
［7］ Itti L, Koch C, Niebur E. A model of saliencybased visual attention for rapid scene analysis［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998,20(11):12541259.
［8］ Zhao Qi, Koch C. Learning a saliency map using fixated locations in natural scenes［J］. Journal of Vision, 2011,11(3):7476.
［9］ Borji A. Boosting bottomup and topdown visual features for saliency estimation［C］// Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition. 2012:438445.
［10］Han Biao, Zhu Hao, Ding Youdong. Bottomup saliency based on weighted sparse coding residual［C］// Proceedings of the 19th ACM International Conference on Multimedia. 2011:11171120.
［11］ Zhang Lingyun, Tong M H, Marks T K, et al. SUN: A Bayesian framework for saliency using natural statistics［J］. Journal of Vision, 2008,8(7), doi: 10.1167/8.7.32. 
［12］Han Junwei, He Sheng, Qian Xiaoliang, et al. An objectoriented visual saliency detection framework based on sparse coding representations［J］. IEEE Transactions on Circuits and Systems for Video Technology, 2013,23(12):20092021.
［13］Bruce N D B, Tsotsos J K. Saliency, attention, and visual search: An information theoretic approach［J］. Journal of Vision, 2009,9(3), doi: 10.1167/9.3.5.
［14］Borji A, Itti L. Exploiting local and global patch rarities for saliency detection［C］// Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition. 2012:478485.
［15］Judd T, Ehinger K, Durand F, et al. Learning to predict where humans look［C］// Proceedings of the 12th International Conference on Computer Vision. 2009:21062113.
［16］Cerf M, Harel J, Einhuser W, et al. Predicting human gaze using lowlevel saliency combined with face detection［C］// Proceedings of the 20th International Conference on Neural Information Processing Systems. 2007:241248.
［17］Shen Chengyao, Song Mingli, Zhao Qi. Learning highlevel concepts by training a deep network on eye fixations［C］// Proceedings of the 2012 NIPS Workshop on Deep Learning and Unsupervised Feature Learning. 2012.
［18］Lin Yuetan, Kong Shu, Wang Donghui, et al. Saliency detection within a deep convolutional architecture［C］// Workshops at the 28th AAAI Conference on Artificial Intelligence. 2014:3137.
［19］Han Junwei, Zhang Dingwen, Wen Shifeng, et al. Twostage learning to predict human eye fixations via SDAEs［J］. IEEE Transactions on Cybernetics, 2016,46(2):487498.
［20］Li Hongyang, Chen Jiang, Lu Huchuan, et al. CNN for saliency detection with lowlevel feature integration［J］. Neurocomputing, 2017,226:212220.
［21］Bruce N D B, Tsotsos J K. Saliency based on information maximization［C］// Proceedings of the 18th International Conference on Neural Information Processing Systems. 2005:155162.
［22］Ramanathan S, Katti H, Sebe N, et al. An eye fixation database for saliency detection in images［C］// Proceedings of the 11th European Conference on Computer Vision. 2010:3043.
［23］Tatler B W, Baddeley R J, Gilchrist I D. Visual correlates of fixation selection: Effects of scale and time［J］. Vision Research, 2005,45(5):643659.
［24］GarciaDiaz A, FdezVidal X R, Pardo X M, et al. Saliency from hierarchical adaptation through decorrelation and variance normalization［J］. Image and Vision Computing, 2012,30(1):5164.
［25］Zhang Jianming, Sclaroff S. Saliency detection: A Boolean map approach［C］// Proceedings of the 2013 IEEE International Conference on Computer Vision. 2013:153160.
［26］Goferman S, ZelnikManor L, Tal A. Contextaware saliency detection［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012,34(10):19151926.
［27］ Hou Xiaodi, Harel J, Koch C. Image signature: Highlighting sparse salient regions［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012,34(1):194201.

[1]	孟娜, 方维维, 路红英. 一种面向微控制器上环境声音分类的DNN压缩方法[J]. 计算机与现代化, 2024, 0(01): 80-86.
[2]	邱凯星, 冯广. 基于双重特征注意力的多标签图像分类模型[J]. 计算机与现代化, 2023, 0(12): 41-47.
[3]	唐诗琪, 周瑞平, 谢仕斌, 刘梦赤, 肖文, . 基于栈式降噪编码器的跨语言多标签情感分类[J]. 计算机与现代化, 2023, 0(11): 6-12.
[4]	吴甜, 刘海华, 童顺延. 基于深度反馈的卷积神经网络的图像分类[J]. 计算机与现代化, 2023, 0(09): 82-86.
[5]	马国祥, 杨凌菲, 严传波, 张志豪, 孙彬, 王晓荣. 基于深度DenseNet网络的肝包虫病超声影像诊断方法[J]. 计算机与现代化, 2023, 0(09): 100-104.
[6]	欧阳飞, 吴旭, 向东升. 基于改进YOLOX的垃圾分类检测方法[J]. 计算机与现代化, 2023, 0(08): 68-73.
[7]	李兰兰, 高建龙, 朱晓, 穆培政. 基于区域内读数段分类的插入/缺失基因组变异检测方法[J]. 计算机与现代化, 2023, 0(07): 13-19.
[8]	秦竹媛, 吴浩忠, 谭代庆, 韩爱庆, 臧昊, 王选, 唐燕. 基于多尺度ResNet融合注意力机制的麦冬细粒度识别[J]. 计算机与现代化, 2023, 0(07): 105-111.
[9]	朱剑波, 葛明锋, 董文飞. 基于改进EfficientNet的阿尔兹海默症图像分类[J]. 计算机与现代化, 2023, 0(06): 56-61.
[10]	叶力鸣, 陈蔚文. 一种结合语义分割和目标检测的级联式绝缘子缺陷检测方法[J]. 计算机与现代化, 2023, 0(06): 82-88.
[11]	华昕宇, 祁云嵩. 一种基于CBAM和改进通道注意力的EfficientNet的混合脑肿瘤分类方法[J]. 计算机与现代化, 2023, 0(05): 1-7.
[12]	王杰, 潘凤, 张艳莎, 谭棉, 严晓波, 王林, . 融合带权非局部模块的铝型材表面缺陷分类[J]. 计算机与现代化, 2023, 0(05): 86-92.
[13]	徐涯昕, 何泽恩, 徐绪堪. 基于CNN-BiLSTM网络的数控机床故障文本自动分类[J]. 计算机与现代化, 2023, 0(04): 7-14.
[14]	魏鑫, 何小海, 滕奇志, 卿粼波, 陈洪刚. 基于BERT-BiLSTM-Attention混合模型的事件抽取方法[J]. 计算机与现代化, 2023, 0(04): 26-31.
[15]	朱原冶, 倪建军, 唐广翼. 一种基于改进卷积神经网络的RGB-D室内场景分类方法[J]. 计算机与现代化, 2023, 0(04): 73-77.