Amharic Language Image Captions Generation Using Hybridized Attention-Based Deep Neural Networks
This study aims to develop a hybridized deep learning model for generating semantically meaningful image captions in Amharic Language. Image captioning is a task that combines both computer vision and natural language processing (NLP) domains. However, existing studies in the English language primar...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2023-01-01
|
| Series: | Applied Computational Intelligence and Soft Computing |
| Online Access: | http://dx.doi.org/10.1155/2023/9397325 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850173760298024960 |
|---|---|
| author | Rodas Solomon Mesfin Abebe |
| author_facet | Rodas Solomon Mesfin Abebe |
| author_sort | Rodas Solomon |
| collection | DOAJ |
| description | This study aims to develop a hybridized deep learning model for generating semantically meaningful image captions in Amharic Language. Image captioning is a task that combines both computer vision and natural language processing (NLP) domains. However, existing studies in the English language primarily focus on visual features to generate captions, resulting in a gap between visual and textual features and inadequate semantic representation. To address this challenge, this study proposes a hybridized attention-based deep neural network (DNN) model. The model consists of an Inception-v3 convolutional neural network (CNN) encoder to extract image features, a visual attention mechanism to capture significant features, and a bidirectional gated recurrent unit (Bi-GRU) with attention decoder to generate the image captions. The model was trained on the Flickr8k and BNATURE datasets with English captions, which were translated into Amharic Language with the help of Google Translator and Amharic Language experts. The evaluation of the model showed improvement in its performance, with a 1G-BLEU score of 60.6, a 2G-BLEU score of 50.1, a 3G-BLEU score of 43.7, and a 4G-BLEU score of 38.8. Generally, this study highlights the effectiveness of the hybrid approach in generating Amharic Language image captions with better semantic meaning. |
| format | Article |
| id | doaj-art-ca6b903e0d644cde8cb73025f4cb5a44 |
| institution | OA Journals |
| issn | 1687-9732 |
| language | English |
| publishDate | 2023-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Applied Computational Intelligence and Soft Computing |
| spelling | doaj-art-ca6b903e0d644cde8cb73025f4cb5a442025-08-20T02:19:47ZengWileyApplied Computational Intelligence and Soft Computing1687-97322023-01-01202310.1155/2023/9397325Amharic Language Image Captions Generation Using Hybridized Attention-Based Deep Neural NetworksRodas Solomon0Mesfin Abebe1Department of Computer Science and EngineeringDepartment of Computer Science and EngineeringThis study aims to develop a hybridized deep learning model for generating semantically meaningful image captions in Amharic Language. Image captioning is a task that combines both computer vision and natural language processing (NLP) domains. However, existing studies in the English language primarily focus on visual features to generate captions, resulting in a gap between visual and textual features and inadequate semantic representation. To address this challenge, this study proposes a hybridized attention-based deep neural network (DNN) model. The model consists of an Inception-v3 convolutional neural network (CNN) encoder to extract image features, a visual attention mechanism to capture significant features, and a bidirectional gated recurrent unit (Bi-GRU) with attention decoder to generate the image captions. The model was trained on the Flickr8k and BNATURE datasets with English captions, which were translated into Amharic Language with the help of Google Translator and Amharic Language experts. The evaluation of the model showed improvement in its performance, with a 1G-BLEU score of 60.6, a 2G-BLEU score of 50.1, a 3G-BLEU score of 43.7, and a 4G-BLEU score of 38.8. Generally, this study highlights the effectiveness of the hybrid approach in generating Amharic Language image captions with better semantic meaning.http://dx.doi.org/10.1155/2023/9397325 |
| spellingShingle | Rodas Solomon Mesfin Abebe Amharic Language Image Captions Generation Using Hybridized Attention-Based Deep Neural Networks Applied Computational Intelligence and Soft Computing |
| title | Amharic Language Image Captions Generation Using Hybridized Attention-Based Deep Neural Networks |
| title_full | Amharic Language Image Captions Generation Using Hybridized Attention-Based Deep Neural Networks |
| title_fullStr | Amharic Language Image Captions Generation Using Hybridized Attention-Based Deep Neural Networks |
| title_full_unstemmed | Amharic Language Image Captions Generation Using Hybridized Attention-Based Deep Neural Networks |
| title_short | Amharic Language Image Captions Generation Using Hybridized Attention-Based Deep Neural Networks |
| title_sort | amharic language image captions generation using hybridized attention based deep neural networks |
| url | http://dx.doi.org/10.1155/2023/9397325 |
| work_keys_str_mv | AT rodassolomon amhariclanguageimagecaptionsgenerationusinghybridizedattentionbaseddeepneuralnetworks AT mesfinabebe amhariclanguageimagecaptionsgenerationusinghybridizedattentionbaseddeepneuralnetworks |