Super-Resolution Convolutional Neural Networks Using Modified and Bilateral ReLU
2019
Super-resolution convolutional neural network (SRCNN) is a deep learning method that reconstructs high-resolution image from low-resolution image. In this paper, we propose to change the ReLU which is the activation function of existing SRCNN, as modified and bilateral ReLU. This modification gives increased number of active nodes and results in improved image quality.
Keywords:
- Correction
- Source
- Cite
- Save
- Machine Reading By IdeaReader
6
References
2
Citations
NaN
KQI