TY  - JOUR
TI  - An Evaluation of VGG16 Binary Classifier Deep Neural Network for Noise and Blur Corrupted Images
AB  - Deep learning networks has become an important tool for image classification applications. Distortions on imagesmay cause the performance of a classifier to decrease significantly. In the present paper, a comparativeinvestigation for binary classification performance of VGG16 network under corrupted inputs has been presented.For this purpose, images corrupted at various levels and fixed levels with Gaussian noise, Salt and Pepper noiseand blur effect were used for testing. Convolutional layers of the VGG16 were frozen except the last threeconvolutional layers and a dense layer for binary classification was added. According to experimental results, asthe effect of distortion is increased, performance of the deep learning classifier drops significantly. In the case ofaugmented training with distortion effects, the results were improved significantly
AU  - Akgün, Devrim
DO  - 10.35377/saucis.03.03.725647
PY  - 2020
JO  - Sakarya University Journal of Computer and Information Sciences  (Online)
VL  - 3
IS  - 3
SN  - 2636-8129
SP  - 264
EP  - 271
DB  - TRDizin
UR  - http://search/yayin/detay/412176
ER  -