RHN: A Residual Holistic Neural Network for Edge Detection

被引：9

作者：

Al-Amaren, Abdullah ^{[1
]}

Ahmad, M. Omair ^{[1
]}

Swamy, M. N. S. ^{[1
]}

机构：

[1] Concordia Univ, Dept Elect & Comp Engn, Montreal, PQ H3G 1M8, Canada

来源：

IEEE ACCESS | 2021年 / 9卷

基金：

加拿大自然科学与工程研究理事会;

关键词：

Image edge detection; Feature extraction; Computer architecture; Training; Task analysis; Residual neural networks; Deep learning; Deep convolutional networks; edge detection; residual learning;

D O I：

10.1109/ACCESS.2021.3078411

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Edge detection plays a very important role in many image processing and computer vision applications. Use of deep convolutional neural networks (DCNNs) has significantly advanced the performance of image edge detection techniques. Existing DCNN techniques, which make use of residual learning, exhibit a good edge detection performance at the expense of an extremely high computational complexity. There are a few VGG16-based DCNN techniques for edge detection that have been proposed with relatively much lower complexity. In this paper, by using the mechanism of residual learning, a new VGG16-based DCNN technique for edge detection is proposed with a view to provide a performance superior to that provided by other such networks while still preserving their low complexity. The proposed network is experimented on different datasets and is shown to outperform all the other VGG16-based techniques designed to solve the problem of edge detection.

引用

页码：74646 / 74658

页数：13

共 44 条

[21]

Javidi B.(., 2002, Image recognition and classification: algorithms, systems, and applications

[22]

Kingma DP, 2015, C TRACK P

[23]

Kokkinos I., 2015, arXiv preprint arXiv:151107386

[24] ImageNet Classification with Deep Convolutional Neural Networks [J].

Krizhevsky, Alex ;

Sutskever, Ilya ;

Hinton, Geoffrey E. .

COMMUNICATIONS OF THE ACM, 2017, 60 (06) :84-90

[25] Edge detection in medical images with quasi high-pass filter based on local statistics [J].

Lin, Wei-Chun ;

Wang, Jing-Wein .

BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2018, 39 :294-302

[26]

Liu Y, 2016, PROC CVPR IEEE, P231, DOI 10.1109/CVPR.2016.32

[27] Richer Convolutional Features for Edge Detection [J].

Liu, Yun ;

Cheng, Ming-Ming ;

Hu, Xiaowei ;

Bian, Jia-Wang ;

Zhang, Le ;

Bai, Xiang ;

Tang, Jinhui .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2019, 41 (08) :1939-1946

[28]

Lowe D. G., 1999, P INT C COMP VIS, V2, P1150, DOI [10.1109/ICCV.1999.790410, DOI 10.1109/ICCV.1999.790410]

[29]

Martin D, 2001, EIGHTH IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION, VOL II, PROCEEDINGS, P416, DOI 10.1109/ICCV.2001.937655

[30] Learning to detect natural image boundaries using local brightness, color, and texture cues [J].

Martin, DR ;

Fowlkes, CC ;

Malik, J .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2004, 26 (05) :530-549

← 1 2 3 4 5 →