Automatic Arabic Image Captioning using RNN-LSTM-Based Language Model and CNN
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2018, Vol 9, Issue 5
Abstract
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.
Authors and Affiliations
Huda A. Al-muzaini, Tasniem N. Al-yahya, Hafida Benhidour
Keywords
Related Articles
- EP ID EP311658
- DOI 10.14569/IJACSA.2018.090610
- Views 160
- Downloads 0
HappyMeter: An Automated System for Real-Time Twitter Sentiment Analysis
The paper presents HappyMeter, an automated system for real-time Twitter sentiment analysis. More than 380 million tweets consisting of nearly 30,000 words, almost 6,000 hashtags and over 5,000 user mentioned have been s...
New Data Clustering Algorithm (NDCA)
Wireless sensor networks (WSNs) have sensing, data processing and communicating capabilities. The major task of the sensor node is to gather the data from the sensed field and send it to the end user via the base station...
Generation of Sokoban Stages using Recurrent Neural Networks
Puzzles and board games represent several important classes of AI problems, but also represent difficult complexity classes. In this paper, we propose a deep learning based alternative to train a neural network model to...
An Artificial Neural Network Application for Estimation of Natural Frequencies of Beams
In this study, natural frequencies of the prismatical steel beams with various geometrical characteristics under the four different boundary conditions are determined using Artificial Neural Network (ANN) technique. In t...
A Two-Level Fault-Tolerance Technique for High Performance Computing Applications
Reliability is the biggest concern facing future extreme-scale, high performance computing (HPC) systems. Within the current generation of HPC systems, projections suggest that errors will occur with very high rates in f...