Automatic image annotation based on deep learning models: A systematic review and future challenges
Recently, much attention has been given to image annotation due to the massive increase in image data volume. One of the image retrieval methods which guarantees the retrieval of images in the same way as texts are automatic image annotation (AIA). Consequently, numerous studies have been conducted...
Saved in:
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Institute of Electrical and Electronics Engineers Inc.
2021
|
Subjects: | |
Online Access: | http://eprints.utm.my/id/eprint/95896/1/MohdShafry2021_AutomaticImageAnnotationBasedonDeepLearningModels.pdf http://eprints.utm.my/id/eprint/95896/ http://dx.doi.org/10.1109/ACCESS.2021.3068897 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my.utm.95896 |
---|---|
record_format |
eprints |
spelling |
my.utm.958962022-06-22T07:19:41Z http://eprints.utm.my/id/eprint/95896/ Automatic image annotation based on deep learning models: A systematic review and future challenges Adnan, Myasar Mundher Mohd. Rahim, Mohd. Shafry Rehman, Amjad Mehmood, Zahid Saba, Tanzila Naqvi, Rizwan Ali QA75 Electronic computers. Computer science Recently, much attention has been given to image annotation due to the massive increase in image data volume. One of the image retrieval methods which guarantees the retrieval of images in the same way as texts are automatic image annotation (AIA). Consequently, numerous studies have been conducted on AIA, particularly on the classification-based and probabilistic modeling techniques. Several image annotation techniques that performed reasonably on standard datasets have been developed over the last decade. In this paper, a review of the image annotation method was conducted, focusing more on deep learning models. Automatic image annotation (AIA) methods were also classified into five categories, including i) Convolutional Neural Network (CNN) based on AIA, ii) Recurrent Neural Network (RNN) based on AIA, iii) Deep Neural Networks (DNN) based on AIA, iv) Long-Short-Term Memory (LSTM) based on AIA, and v) Stacked auto-encoder (SAE) based on AIA. An assessment of the five varieties of AIA methods was also offered based on their principal notion, feature mining technique, explanation precision, computational density, and examined aggregated data. Moreover, the evaluation metrics used to evaluate AIA methods were reviewed and discussed. The need for careful consideration of methods throughout the improvement of novel procedures and datasets for image annotation assignment was highly demanded. From the analysis of the achievements so far, it is certain that more attention should be paid to automatic image annotation. Institute of Electrical and Electronics Engineers Inc. 2021 Article PeerReviewed application/pdf en http://eprints.utm.my/id/eprint/95896/1/MohdShafry2021_AutomaticImageAnnotationBasedonDeepLearningModels.pdf Adnan, Myasar Mundher and Mohd. Rahim, Mohd. Shafry and Rehman, Amjad and Mehmood, Zahid and Saba, Tanzila and Naqvi, Rizwan Ali (2021) Automatic image annotation based on deep learning models: A systematic review and future challenges. IEEE Access, 9 . pp. 50253-50264. ISSN 2169-3536 http://dx.doi.org/10.1109/ACCESS.2021.3068897 |
institution |
Universiti Teknologi Malaysia |
building |
UTM Library |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Teknologi Malaysia |
content_source |
UTM Institutional Repository |
url_provider |
http://eprints.utm.my/ |
language |
English |
topic |
QA75 Electronic computers. Computer science |
spellingShingle |
QA75 Electronic computers. Computer science Adnan, Myasar Mundher Mohd. Rahim, Mohd. Shafry Rehman, Amjad Mehmood, Zahid Saba, Tanzila Naqvi, Rizwan Ali Automatic image annotation based on deep learning models: A systematic review and future challenges |
description |
Recently, much attention has been given to image annotation due to the massive increase in image data volume. One of the image retrieval methods which guarantees the retrieval of images in the same way as texts are automatic image annotation (AIA). Consequently, numerous studies have been conducted on AIA, particularly on the classification-based and probabilistic modeling techniques. Several image annotation techniques that performed reasonably on standard datasets have been developed over the last decade. In this paper, a review of the image annotation method was conducted, focusing more on deep learning models. Automatic image annotation (AIA) methods were also classified into five categories, including i) Convolutional Neural Network (CNN) based on AIA, ii) Recurrent Neural Network (RNN) based on AIA, iii) Deep Neural Networks (DNN) based on AIA, iv) Long-Short-Term Memory (LSTM) based on AIA, and v) Stacked auto-encoder (SAE) based on AIA. An assessment of the five varieties of AIA methods was also offered based on their principal notion, feature mining technique, explanation precision, computational density, and examined aggregated data. Moreover, the evaluation metrics used to evaluate AIA methods were reviewed and discussed. The need for careful consideration of methods throughout the improvement of novel procedures and datasets for image annotation assignment was highly demanded. From the analysis of the achievements so far, it is certain that more attention should be paid to automatic image annotation. |
format |
Article |
author |
Adnan, Myasar Mundher Mohd. Rahim, Mohd. Shafry Rehman, Amjad Mehmood, Zahid Saba, Tanzila Naqvi, Rizwan Ali |
author_facet |
Adnan, Myasar Mundher Mohd. Rahim, Mohd. Shafry Rehman, Amjad Mehmood, Zahid Saba, Tanzila Naqvi, Rizwan Ali |
author_sort |
Adnan, Myasar Mundher |
title |
Automatic image annotation based on deep learning models: A systematic review and future challenges |
title_short |
Automatic image annotation based on deep learning models: A systematic review and future challenges |
title_full |
Automatic image annotation based on deep learning models: A systematic review and future challenges |
title_fullStr |
Automatic image annotation based on deep learning models: A systematic review and future challenges |
title_full_unstemmed |
Automatic image annotation based on deep learning models: A systematic review and future challenges |
title_sort |
automatic image annotation based on deep learning models: a systematic review and future challenges |
publisher |
Institute of Electrical and Electronics Engineers Inc. |
publishDate |
2021 |
url |
http://eprints.utm.my/id/eprint/95896/1/MohdShafry2021_AutomaticImageAnnotationBasedonDeepLearningModels.pdf http://eprints.utm.my/id/eprint/95896/ http://dx.doi.org/10.1109/ACCESS.2021.3068897 |
_version_ |
1736833522080940032 |
score |
13.18916 |