Automatic Arabic Image Captioning using RNN-LSTM-Based Language Model and CNN

The automatic generation of correct syntaxial and semantical image captions is an essential problem in Artificial Intelligence. The existence of large image caption copra such as Flickr and MS COCO have contributed to the advance of image captioning in English. However, it is still behind for Arabic given the scarcity of image caption corpus for the Arabic language. In this work, an Arabic version that is a part of the Flickr and MS COCO caption dataset is built. Moreover, a generative merge model for Arabic image captioning based on a deep RNN-LSTM and CNN model is developed. The results of the experiments are promising and suggest that the merge model can achieve excellent results for Arabic image captioning if a larger corpus is used.

@article{Al-muzaini2018,
  title     = {Automatic Arabic Image Captioning using RNN-LSTM-Based Language Model and CNN},
  journal   = {International Journal of Advanced Computer Science and Applications},
  volume    = {9},
  number    = {6},
  year      = {2018},
  publisher = {The Science and Information Organization},
  author    = {Huda A. Al-muzaini and Tasniem N. Al-yahya and Hafida Benhidour},
  doi       = {10.14569/IJACSA.2018.090610},
  url       = {https://doi.org/10.14569/IJACSA.2018.090610}
}