Detecting Errors in Automatic Image Captioning by Deep Learning

Abstract

Automatic tagging of images is an important research topic in the field of image processing. Another area similar to this is the automatic generation of picture captions. In this study, a deep learning model that automatically tags the pictures is used to detect errors in image captions. As a result of the initial experiments, it is observed that the proposed system can find up to 80% of the errors in the image captions.