http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
CNN 기반 잡음 제거: layer 크기에 따른 커널 복원
안준현(Junhyun Ahn),백종덕(Jongduck Baek) 대한전자공학회 2019 대한전자공학회 학술대회 Vol.2019 No.11
CNN (Convolutional Neural Network) is one of the deep learning techniques for analyzing images and images. In this paper, we analyze the denoising performance of CNN with respect to the layer size for quarter dose XCAT images. The results shows that there are suitable layer size for denoising images. In addition, reconstructed images with error function MSE and VGG16 decrease high frequency level. Also using bif convolution layer can make lines along the boundary.