Convolutional Neural Network Architectures Used in Computer Vision
Ferit Can, Can Eyüpoğlu · 2021 5th International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT) · 2021
Studies on computer vision have gained momentum especially with the development of convolutional neural networks (CNN). In addition, the creation of better data sets in terms of quality and quantity, providing access to these data sets, developments in computational power and parallel programming are other issues that affect the achievement of high levels of accuracy. In this study, the concept of computer vision, the factors that make computer vision difficult, the studies that have been done in computer vision until today are summarized. The algorithms developed for this purpose are examined and the studies done in the last five years are analyzed and presented comparatively. With this study, it is aimed to provide a general perspective for future studies.