Reversed Image Detection with Convolutional Neural Networks

Automatic image orientation detection is an important image processing problem, although many studies have been done on this subject. In this paper, we used Convolutional Neural Networks(CNN) to detect 0 and 180 oriented images. Each image of the data set we have used contains only one object. Thanks to this, we have demonstrated that the success of the model depends on the image class selected in the training and testing.