当前位置>主页 > 期刊在线 > 信息技术 >

信息技术21年10期

深度学习技术在智能图像处理中的应用研究
张克智¹,魏国强¹,冯泽 ²,高恩双 ³,宁锋¹
(1. 南宁师范大学 物理与电子学院,广西 南宁 530001;2. 广西理工职业技术学校,广西 南宁 530031;3. 南宁师范大学 环境与生命科学学院,广西 南宁 530001)

摘  要:人工智能已覆盖诸多领域,尤其是在图像处理领域的应用已经十分成熟。作为深度学习典型算法的卷积神经网络在图像处理领域大放异彩,长久以来一直是学术界研究的热点。文章给出了图像处理的概念,简述了卷积神经网络及其在图像处理中所用到的几种典型模型,最后浅谈智能图像处理的未来发展趋势。


关键词:图像处理;深度学习;卷积神经网络



DOI:10.19850/j.cnki.2096-4706.2021.10.004


中图分类号:TP391.1;TP181                          文献标识码:A                                   文章编号:2096-4706(2021)10-0015-06


Research on Application of Deep Learning Technology in Intelligent Image Processing

ZHANG Kezhi 1 ,WEI Guoqiang1 ,FENG Ze 2 ,GAO Enshuang3 ,NING Feng1

(1.School of Physics and Electronics,Nanning Normal University,Nanning 530001,China; 2.Guangxi Polytechnic Vocational Technical School,Nanning 530031,China; 3.School of Environment and Life Science,Nanning Normal University,Nanning 530001,China)

Abstract:Artificial intelligence has been applied in many fields,especially in the field of image processing,the application has been very mature. As a typical algorithm of deep learning,convolutional neural network shines brightly in the field of image processing and has been a research hotspot in the academic circle for a long time. This paper gives the concept of image processing,briefly describes convolutional neural network and several typical models used in image processing,and finally discusses the future development trend of intelligent image processing.

Keywords:image processing;deep learning;convolutional neural network


参考文献:

[1] 胡学龙 . 数字图像处理:第 4 版 [M]. 北京:电子工业出 版社,2020.

[2] LECUN Y,BOTTOU L,BENGIO Y,et al. Gradient-based learning applied to document recognition [J].IEEE,1998,86(11): 2278-2324.

[3] 赵卫东,董亮 . 机器学习 [M]. 北京:人民邮电出版社, 2018.

[4] 郑远攀,李广阳,李晔 . 深度学习在图像识别中的应用研 究综述 [J]. 计算机工程与应用,2019,55(12):20-36.

[5] KRIZHEVSKY A,SUTSKEVER I,HINTON G E. ImageNet classification with deep convolutional neural networks [C]//Advances in Neural Information Processing Systems.London:MIT Press,2012: 1097-1105.

[6] SIMONYAN K,ZISSERMAN A. Very deep convolutional networks for large-scale Image recognition [J/OL].arXiv:1409.1556 [cs. CV].(2015-04-10).https://arxiv.org/abs/1409.1556.

[7] SZEGEDY C,LIU W,JIA Y Q,et al. Going deeper with convolutions [C]//2015 IEEE Conference on Computer Vision and Pattern Recognition(CVPR).Boston:IEEE,2015:1-9.

[8] 彭璟,罗浩宇,赵淦森,等 . 深度学习下的医学影像分割 算法综述 [J]. 计算机工程与应用,2021,57(3):44-57.

[9] 杨佳晴 . 基于场景配准的图像特征提取算法研究 [D]. 成 都:电子科技大学,2019.

[10] 唐灿,唐亮贵,刘波 . 图像特征检测与匹配方法研究综 述 [J]. 南京信息工程大学学报(自然科学版),2020,12(3): 261-273.

[11] 张婷婷,章坚武,郭春生,等 . 基于深度学习的图像目 标检测算法综述 [J]. 电信科学,2020,36(7):92-106.

[12] AGRAWAL P,GIRSHICK R,MALIK J. Analyzing the performance of Multilayer Neural Networks for Object Recognition [J]. Lecture Notes in Computer Science,2014:329-344.

[13] GIRSHICK R. Fast R-CNN [C]//2015 IEEE International Conference on Computer Vision(ICCV).Santiago:IEEE,2015: 1440-1448.

[14] REN S Q,HE K M,GIRSHICK R,et al. Faster R-CNN: towards real-time object detection with region proposal networks [J]. IEEE Transactions on Pattern Analysis & Machine Intelligence,2015, 39(6):1137-1149.

[15] REDNON J,DIVVALA S,GIRSHICK R,et al. You only look once:unified,real-time object detection [C]//2016 IEEE Conference on Computer Vision and Pattern Recognition(CVPR).Las Vegas:IEEE,2016:779-788.

[16] 杨露菁,吉文阳,郝卓楠,等 . 智能图像处理及应用 [M]. 北京:中国铁道出版社,2019.

[17] 盖荣丽,蔡建荣,王诗宇,等 . 卷积神经网络在图像识 别中的应用研究综述 [J]. 小型微型计算机系统,2021,42(9): 1980-1984.

[18] 朱云,凌志刚,张雨强.机器视觉技术研究进展及展望 [J]. 图学学报,2020,41(6):871-890.


作者简介:张克智(1982.09—),男,汉族,山东济宁人, 讲师,博士,研究方向:人工智能、图像处理、电子材料;通讯作 者:高恩双(1987.01—),女,汉族,山东临沂人,实验员,硕士, 研究方向:人工智能、环境与化学。