Open Access
ARTICLE
The Instance-Aware Automatic Image Colorization Based on Deep Convolutional Neural Network
Hui Li1, Wei Zeng1,*, Guorong Xiao2, Huabin Wang1
1 School of Information Science and Technology, Huizhou University, Huizhou 516000, Guangdong, China
2 Key Laboratory of Science & Technology and Finance, Guangdong University of Finance, Guangzhou 510521, Guangdong, China
* Corresponding Authors: Wei Zeng, , Guorong Xiao
Intelligent Automation & Soft Computing 2020, 26(4), 841-846. https://doi.org/10.32604/iasc.2020.010118
Abstract
Recent progress on image colorization is substantial and benefiting mostly from
the great development of the deep convolutional neural networks. However,
one type of object can be colored by different kinds of colors. Due to the
uncertain relationship between the object and color, the deep neural network is
unstable and difficult to converge during the training process. In order to solve
this problem, this paper proposes an instance-aware automatic image
colorization algorithm, which uses the semantic features of the object instance
as prior knowledge to guide the deep neural network to do the colorization
task. Meanwhile, we design a discrete loss function to train the deep network
and this network can be trained from end to end. Experiments show that this
algorithm can obtain satisfactory colorful results on the images containing
object instance and achieves state-of-the-art results.
Keywords
Cite This Article
H. Li, W. Zeng, G. Xiao and H. Wang, "The instance-aware automatic image colorization based on deep convolutional neural network,"
Intelligent Automation & Soft Computing, vol. 26, no.4, pp. 841–846, 2020. https://doi.org/10.32604/iasc.2020.010118