Research on Image Colorization Algorithm Based on Residual Neural Network

被引：5
|
作者：
Qin, Pinle [1 ]
Cheng, Zirui [1 ]
Cui, Yuhao [1 ]
Zhang, Jinjing [1 ]
Miao, Qiguang [2 ]
机构：
[1] North Univ China, Sch Comp & Control Engn, Taiyuan 030051, Shanxi, Peoples R China
[2] Xidian Univ, Sch Comp Sci & Technol, Xian 710075, Shaanxi, Peoples R China
来源：
COMPUTER VISION, PT I | 2017年 / 771卷
关键词：
Residual neural network; Image colorization; Non-linear map; Grayscale image;
D O I：
10.1007/978-981-10-7299-4_51
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
In order to colorize the grayscale images efficiently, an image colorization method based on deep residual neural network is proposed. This method combines the classified information and features of the image, uses the whole image as the input of the network and forms a non-linear mapping from grayscale images to the colorful images through the deep network. The network is trained by using the MIT Places Database and ImageNet and colorizes the grayscale images. The experiment result shows that different data sets have different colorization effects on grayscale images, and the complexity of the network determines the colorization effect of grayscale images. This method can colorize the grayscale images efficiently, which has better visual effect.
引用
收藏
页码：608 / 621
页数：14
相关论文
共 50 条
  • [31] Gray image colorization algorithm based on image segmentation and region matching
    Huang Guan-ting
    Han Xue-hui
    Gong Xiao-ting
    Wang Xiao-yu
    Zhu Yong
    Duan Jin
    CHINESE JOURNAL OF LIQUID CRYSTALS AND DISPLAYS, 2019, 34 (06) : 619 - 626
  • [32] Research on Segmentation Algorithm for 3D Medical Image Based on Neural Network
    Lin, Xiao-mei
    Song, Wei
    ICNC 2008: FOURTH INTERNATIONAL CONFERENCE ON NATURAL COMPUTATION, VOL 2, PROCEEDINGS, 2008, : 517 - 521
  • [33] Automatic Cartoon Colorization Based on Convolutional Neural Network
    Varga, Domonkos
    Szabo, Csaba Attila
    Sziranyi, Tamas
    PROCEEDINGS OF THE 15TH INTERNATIONAL WORKSHOP ON CONTENT-BASED MULTIMEDIA INDEXING (CBMI), 2017,
  • [34] Research on Product Image Styling Design Method Based on Neural Network and Genetic Algorithm
    Su, Jianning
    Jiang, Yuhong
    Wang, Peng
    ICNC 2008: FOURTH INTERNATIONAL CONFERENCE ON NATURAL COMPUTATION, VOL 5, PROCEEDINGS, 2008, : 603 - +
  • [35] Research on visualisation algorithm of handwritten digital image recognition based on deep neural network
    Teng, Fang
    Hu, Xingliu
    INTERNATIONAL JOURNAL OF COMPUTER APPLICATIONS IN TECHNOLOGY, 2023, 72 (01) : 69 - 76
  • [36] Research on Image Edge Detection Algorithm Based on Eigenvector and Improved BP Neural Network
    Yu, Mingyang
    Huang, Xiaoyu
    PROCEEDINGS OF THE ADVANCES IN MATERIALS, MACHINERY, ELECTRICAL ENGINEERING (AMMEE 2017), 2017, 114 : 667 - 673
  • [37] A mine image reconstruction method based on residual neural network
    Zhang F.
    Xu Z.
    Meitan Xuebao/Journal of the China Coal Society, 2019, 44 (11): : 3614 - 3624
  • [38] Detection of Corneal Ulcer Using a Genetic Algorithm-Based Image Selection and Residual Neural Network
    Inneci, Tugba
    Badem, Hasan
    BIOENGINEERING-BASEL, 2023, 10 (06):
  • [39] Image Classification Algorithm Based on Improved Deep Residual Network
    Chu Y.-Z.
    Wang J.-Q.
    Zhang X.-F.
    Liu H.
    Dianzi Keji Daxue Xuebao/Journal of the University of Electronic Science and Technology of China, 2021, 50 (02): : 243 - 248
  • [40] Wood Identification Algorithm Based on Improved Residual Neural Network
    Su H.
    Lü J.
    Ding Z.
    Tang Y.
    Chen X.
    Zhou Q.
    Zhang Z.
    Yao Q.
    Linye Kexue/Scientia Silvae Sinicae, 2021, 57 (12): : 147 - 154
12345