Back to Search
Start Over
Fully automatic image colorization based on semantic segmentation technology
- Source :
- PLoS ONE, PLoS ONE, Vol 16, Iss 11, p e0259953 (2021)
- Publication Year :
- 2021
- Publisher :
- Public Library of Science (PLoS), 2021.
-
Abstract
- Aiming at these problems of image colorization algorithms based on deep learning, such as color bleeding and insufficient color, this paper converts the study of image colorization to the optimization of image semantic segmentation, and proposes a fully automatic image colorization model based on semantic segmentation technology. Firstly, we use the encoder as the local feature extraction network and use VGG-16 as the global feature extraction network. These two parts do not interfere with each other, but they share the low-level feature. Then, the first fusion module is constructed to merge local features and global features, and the fusion results are input into semantic segmentation network and color prediction network respectively. Finally, the color prediction network obtains the semantic segmentation information of the image through the second fusion module, and predicts the chrominance of the image based on it. Through several sets of experiments, it is proved that the performance of our model becomes stronger and stronger under the nourishment of the data. Even in some complex scenes, our model can predict reasonable colors and color correctly, and the output effect is very real and natural.
- Subjects :
- Technology
Computer science
Vascular Medicine
Grayscale
Remote Sensing
Mathematical and Statistical Techniques
Geoinformatics
Image Processing, Computer-Assisted
Photography
Medicine and Health Sciences
Segmentation
Coloring Agents
Remote Sensing Imagery
Multidisciplinary
Geography
Applied Mathematics
Simulation and Modeling
Semantics
Feature (computer vision)
Physical Sciences
Chrominance
Medicine
Engineering and Technology
Color bleeding
Colorimetry
Encoder
Algorithms
Research Article
Computer and Information Sciences
Neural Networks
Imaging Techniques
Science
Feature extraction
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
Color
Hemorrhage
Digital Imaging
Research and Analysis Methods
Deep Learning
Signs and Symptoms
Semantic Web
business.industry
Deep learning
Biology and Life Sciences
Pattern recognition
Convolution
Computer Science::Computer Vision and Pattern Recognition
Earth Sciences
Neural Networks, Computer
Artificial intelligence
Clinical Medicine
business
Mathematical Functions
Mathematics
Neuroscience
Subjects
Details
- ISSN :
- 19326203
- Volume :
- 16
- Database :
- OpenAIRE
- Journal :
- PLOS ONE
- Accession number :
- edsair.doi.dedup.....dc10c64cbd743290dda2868c8ecc4bc9