Detecting Errors in Automatic Image Captioning by Deep Learning Derin Ögrenme ile Otomatik Olarak Üretilen Resim Alt Yazismdaki Hatalarm Tespiti

Karakaya K. M.

6th International Conference on Computer Science and Engineering, UBMK 2021, Ankara, Turkey, 15 - 17 September 2021, pp.46-49, (Full Text) identifier

  • Publication Type: Conference Paper / Full Text
  • Doi Number: 10.1109/ubmk52708.2021.9558968
  • City: Ankara
  • Country: Turkey
  • Page Numbers: pp.46-49
  • Keywords: Captioning, Deep learning, Deep neural networks, Error detection, Image processing, Tagging
  • TED University Affiliated: Yes

Abstract

Automatic tagging of images is an important researcli topic in tlie field of image processing. Anotlier 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.